2025-10-31 15:04:36.429899: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:04:36.441830: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761919476.456032 1591802 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761919476.460423 1591802 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761919476.471123 1591802 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761919476.471156 1591802 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761919476.471159 1591802 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761919476.471162 1591802 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:04:36.474569: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
/home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/tune/impl/tuner_internal.py:144: RayDeprecationWarning: The `RunConfig` class should be imported from `ray.tune` when passing it to the Tuner. Please update your imports. See this issue for more context and migration options: https://github.com/ray-project/ray/issues/49454. Disable these warnings by setting the environment variable: RAY_TRAIN_ENABLE_V2_MIGRATION_WARNINGS=0
  _log_deprecation_warning(
2025-10-31 15:04:39,675	INFO worker.py:1927 -- Started a local Ray instance.
2025-10-31 15:04:40,405	INFO tune.py:253 -- Initializing Ray automatically. For cluster usage or custom Ray initialization, call `ray.init(...)` before `Tuner(...)`.
2025-10-31 15:04:40,479	INFO trial.py:182 -- Creating a new dirname dir_8b084_3788 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,483	INFO trial.py:182 -- Creating a new dirname dir_8b084_7a01 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,485	INFO trial.py:182 -- Creating a new dirname dir_8b084_dc64 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,488	INFO trial.py:182 -- Creating a new dirname dir_8b084_2e5a because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,490	INFO trial.py:182 -- Creating a new dirname dir_8b084_d6bd because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,493	INFO trial.py:182 -- Creating a new dirname dir_8b084_5242 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,496	INFO trial.py:182 -- Creating a new dirname dir_8b084_6955 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,498	INFO trial.py:182 -- Creating a new dirname dir_8b084_2a3e because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,499	INFO trial.py:182 -- Creating a new dirname dir_8b084_8cb2 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,503	INFO trial.py:182 -- Creating a new dirname dir_8b084_bb95 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,505	INFO trial.py:182 -- Creating a new dirname dir_8b084_2182 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,508	INFO trial.py:182 -- Creating a new dirname dir_8b084_80a3 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,510	INFO trial.py:182 -- Creating a new dirname dir_8b084_1b43 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,513	INFO trial.py:182 -- Creating a new dirname dir_8b084_df2d because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,517	INFO trial.py:182 -- Creating a new dirname dir_8b084_f099 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,520	INFO trial.py:182 -- Creating a new dirname dir_8b084_288b because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,524	INFO trial.py:182 -- Creating a new dirname dir_8b084_23c3 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,530	INFO trial.py:182 -- Creating a new dirname dir_8b084_c502 because trial dirname 'dir_8b084' already exists.
2025-10-31 15:04:40,536	INFO trial.py:182 -- Creating a new dirname dir_8b084_7835 because trial dirname 'dir_8b084' already exists.
1 GPU(s) detected and VRAM set to crossover mode..
Se lanza la búsqueda de hiperparámetros óptimos del modelo
╭─────────────────────────────────────────────────────────────────────╮
│ Configuration for experiment     CAPTURE24_hyperparameters_tuning   │
├─────────────────────────────────────────────────────────────────────┤
│ Search algorithm                 BasicVariantGenerator              │
│ Scheduler                        FIFOScheduler                      │
│ Number of trials                 20                                 │
╰─────────────────────────────────────────────────────────────────────╯

View detailed results here: /mnt/nvme1n2/git/uniovi-simur-wearablepermed-data/output/Paper_results/cases_dataset_C/case_C_CAPTURE24_acc_gyr_17_classes/CAPTURE24_hyperparameters_tuning
To visualize your results with TensorBoard, run: `tensorboard --logdir /tmp/ray/session_2025-10-31_15-04-38_964005_1591802/artifacts/2025-10-31_15-04-40/CAPTURE24_hyperparameters_tuning/driver_artifacts`

Trial status: 20 PENDING
Current time: 2025-10-31 15:04:40. Total running time: 0s
Logical resource usage: 0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    PENDING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    PENDING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    PENDING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    PENDING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    PENDING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    PENDING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    PENDING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    PENDING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    PENDING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    PENDING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    PENDING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    PENDING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    PENDING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    PENDING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    PENDING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    PENDING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    PENDING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    PENDING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    PENDING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    PENDING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            25 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00007 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            21 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            29 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00004 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            18 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00004 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            16 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            24 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            20 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00003 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            22 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            29 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00017 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            27 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00003 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            23 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00007 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            22 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00018 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            22 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00018 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            25 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00016 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            21 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00017 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            17 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00012 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            29 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00011 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            15 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00004 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            28 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_8b084 started with configuration:
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:43.769786: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:43.790579: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
[36m(train_cnn_ray_tune pid=1593421)[0m WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
[36m(train_cnn_ray_tune pid=1593421)[0m E0000 00:00:1761919483.817973 1594582 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
[36m(train_cnn_ray_tune pid=1593421)[0m E0000 00:00:1761919483.825757 1594582 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
[36m(train_cnn_ray_tune pid=1593421)[0m W0000 00:00:1761919483.845325 1594582 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
[36m(train_cnn_ray_tune pid=1593421)[0m W0000 00:00:1761919483.845359 1594582 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
[36m(train_cnn_ray_tune pid=1593421)[0m W0000 00:00:1761919483.845362 1594582 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
[36m(train_cnn_ray_tune pid=1593421)[0m W0000 00:00:1761919483.845364 1594582 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:43.851437: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
[36m(train_cnn_ray_tune pid=1593421)[0m To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:47.107848: E external/local_xla/xla/stream_executor/cuda/cuda_platform.cc:51] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:47.107894: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:167] env: CUDA_VISIBLE_DEVICES=""
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:47.107903: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:170] CUDA_VISIBLE_DEVICES is set to an empty string - this hides all GPUs from CUDA
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:47.107907: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:178] verbose logging is disabled. Rerun with verbose logging (usually --v=1 or --vmodule=cuda_diagnostics=1) to get more diagnostic output from this module
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:47.107912: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:183] retrieving CUDA diagnostic information for host: simur-MS-7B94
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:47.107914: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:190] hostname: simur-MS-7B94
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:47.108120: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:197] libcuda reported version is: 570.133.7
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:47.108172: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:201] kernel reported version is: 570.133.7
[36m(train_cnn_ray_tune pid=1593421)[0m 2025-10-31 15:04:47.108177: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:291] kernel version seems to match DSO: 570.133.7
╭──────────────────────────────────────╮
│ Trial trial_8b084 config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            23 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00003 │
╰──────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593421)[0m Epoch 1/25
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08:03[0m 3s/step - accuracy: 0.1250 - loss: 3.3710
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.1181 - loss: 3.3324  
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1125 - loss: 3.3312
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 18ms/step - accuracy: 0.1024 - loss: 3.3508
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 17ms/step - accuracy: 0.0918 - loss: 3.3754
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 16ms/step - accuracy: 0.0845 - loss: 3.3818
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 15ms/step - accuracy: 0.0811 - loss: 3.3832
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 15ms/step - accuracy: 0.0787 - loss: 3.3860
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 15ms/step - accuracy: 0.0773 - loss: 3.3885
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 15ms/step - accuracy: 0.0761 - loss: 3.3894
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 15ms/step - accuracy: 0.0754 - loss: 3.3884
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 15ms/step - accuracy: 0.0749 - loss: 3.3863
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 16ms/step - accuracy: 0.0746 - loss: 3.3847
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 16ms/step - accuracy: 0.0744 - loss: 3.3839
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 17ms/step - accuracy: 0.0742 - loss: 3.3826
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 16ms/step - accuracy: 0.0739 - loss: 3.3816
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06:09[0m 3s/step - accuracy: 0.0625 - loss: 3.4224
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.0556 - loss: 3.5521  
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 16ms/step - accuracy: 0.0736 - loss: 3.3815
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 16ms/step - accuracy: 0.0731 - loss: 3.3810
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 16ms/step - accuracy: 0.0726 - loss: 3.3807
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.0868 - loss: 3.3381
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.0940 - loss: 3.2811
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.0417 - loss: 3.3545    
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 28ms/step - accuracy: 0.0544 - loss: 3.2703
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.0906 - loss: 3.2622
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  9/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.0873 - loss: 3.2610
[1m 11/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.0849 - loss: 3.2606
[36m(train_cnn_ray_tune pid=1593435)[0m Epoch 1/17[32m [repeated 19x across cluster] (Ray deduplicates logs by default. Set RAY_DEDUP_LOGS=0 to disable log deduplication, or see https://docs.ray.io/en/master/ray-observability/user-guides/configure-logging.html#log-deduplication for more options.)[0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 18/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 31ms/step - accuracy: 0.0788 - loss: 3.2602
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.0312 - loss: 3.6151      
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 29ms/step - accuracy: 0.0381 - loss: 3.6171
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.1810 - loss: 2.9383 
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 55/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 33ms/step - accuracy: 0.0774 - loss: 3.2035
[1m 56/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 33ms/step - accuracy: 0.0775 - loss: 3.2021
[1m 57/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 34ms/step - accuracy: 0.0775 - loss: 3.2008
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.0938 - loss: 3.2175  
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46[0m 91ms/step - accuracy: 0.0781 - loss: 3.4272 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:25[0m 73ms/step - accuracy: 0.0729 - loss: 3.4361
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 70ms/step - accuracy: 0.0703 - loss: 3.4775
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 68ms/step - accuracy: 0.0688 - loss: 3.4988
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 66ms/step - accuracy: 0.0719 - loss: 3.4948
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.0716 - loss: 3.4932
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.0707 - loss: 3.4907
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.0700 - loss: 3.4905
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07:44[0m 7s/step - accuracy: 0.0938 - loss: 3.7493[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 67ms/step - accuracy: 0.0700 - loss: 3.4872
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.0695 - loss: 3.4876
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 35ms/step - accuracy: 0.0780 - loss: 3.2016
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 35ms/step - accuracy: 0.0779 - loss: 3.2018[32m [repeated 161x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.0686 - loss: 3.4873
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.0682 - loss: 3.4868
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.0678 - loss: 3.4868
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.0674 - loss: 3.4863
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m  89/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 35ms/step - accuracy: 0.0612 - loss: 3.4041[32m [repeated 157x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.0658 - loss: 3.4858
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.0652 - loss: 3.4875
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0649 - loss: 3.4887
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0645 - loss: 3.4903
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03:13[0m 7s/step - accuracy: 0.0312 - loss: 3.7040
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 72ms/step - accuracy: 0.0469 - loss: 3.6404  [32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.0642 - loss: 3.4916
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.0639 - loss: 3.4931
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0637 - loss: 3.4948
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.0634 - loss: 3.4962
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 31/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 62ms/step - accuracy: 0.0730 - loss: 3.4881
[1m 32/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 63ms/step - accuracy: 0.0728 - loss: 3.4862[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 90/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 55ms/step - accuracy: 0.0701 - loss: 3.3918[32m [repeated 178x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.0613 - loss: 3.5081
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.0611 - loss: 3.5097
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.0608 - loss: 3.5110
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.0606 - loss: 3.5121
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.0600 - loss: 3.5144
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.0599 - loss: 3.5148
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.0597 - loss: 3.5150
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.0595 - loss: 3.5152
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.0604 - loss: 3.5131[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.0595 - loss: 3.5152
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.0594 - loss: 3.5151
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.0593 - loss: 3.5151
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.0593 - loss: 3.5149
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.0593 - loss: 3.5147
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.0593 - loss: 3.5144
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.0593 - loss: 3.5141
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.0593 - loss: 3.5136
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.0593 - loss: 3.5128
[1m  59/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.0594 - loss: 3.5123
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.0594 - loss: 3.5118
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.0595 - loss: 3.5112
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.0595 - loss: 3.5107
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.0595 - loss: 3.5102
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 37ms/step - accuracy: 0.0720 - loss: 3.3487
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 36ms/step - accuracy: 0.0723 - loss: 3.3473
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 36ms/step - accuracy: 0.0725 - loss: 3.3459
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.0598 - loss: 3.5078
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.0599 - loss: 3.5073
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.0605 - loss: 3.5044
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.0606 - loss: 3.5040
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m248/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0721 - loss: 3.3608
[1m251/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0721 - loss: 3.3604
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.0606 - loss: 3.5036
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.0607 - loss: 3.5032
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m253/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0722 - loss: 3.3602
[1m255/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0722 - loss: 3.3599
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m257/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.0722 - loss: 3.3597
[1m259/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0722 - loss: 3.3594
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.0610 - loss: 3.5019
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.0611 - loss: 3.5016
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m261/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0723 - loss: 3.3592
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.0612 - loss: 3.5013
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.0613 - loss: 3.5010
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m263/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0723 - loss: 3.3589
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m266/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0723 - loss: 3.3586
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m268/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0723 - loss: 3.3583
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m270/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0723 - loss: 3.3581
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m272/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0723 - loss: 3.3579
[1m273/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0724 - loss: 3.3578
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m274/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0724 - loss: 3.3577
[1m276/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0724 - loss: 3.3575
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.0618 - loss: 3.4986
[1m  92/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.0619 - loss: 3.4982
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m278/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0724 - loss: 3.3572
[1m280/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0724 - loss: 3.3570
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 36ms/step - accuracy: 0.0779 - loss: 3.3161
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 36ms/step - accuracy: 0.0781 - loss: 3.3150[32m [repeated 250x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m282/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0724 - loss: 3.3568
[1m284/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.0725 - loss: 3.3566
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m286/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0725 - loss: 3.3563
[1m288/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0725 - loss: 3.3561
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 64ms/step - accuracy: 0.0623 - loss: 3.4965
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 65ms/step - accuracy: 0.0624 - loss: 3.4960
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m290/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0725 - loss: 3.3558
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m36s[0m 38ms/step - accuracy: 0.0799 - loss: 3.1752[32m [repeated 229x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m292/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0725 - loss: 3.3556
[1m294/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0726 - loss: 3.3553
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m296/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0726 - loss: 3.3551
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m298/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0726 - loss: 3.3549
[1m300/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0726 - loss: 3.3546
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m302/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0726 - loss: 3.3544
[1m304/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0727 - loss: 3.3542
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 65ms/step - accuracy: 0.0630 - loss: 3.4933
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 65ms/step - accuracy: 0.0631 - loss: 3.4928
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m306/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0727 - loss: 3.3540
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 65ms/step - accuracy: 0.0632 - loss: 3.4924
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.0634 - loss: 3.4917
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m308/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0727 - loss: 3.3538
[1m309/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0727 - loss: 3.3537
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m241/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 38ms/step - accuracy: 0.0651 - loss: 3.4488
[1m242/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 38ms/step - accuracy: 0.0652 - loss: 3.4486[32m [repeated 187x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m185/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 49ms/step - accuracy: 0.1027 - loss: 3.0124[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m311/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.0727 - loss: 3.3535
[1m313/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.0728 - loss: 3.3532
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.0637 - loss: 3.4904
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.0638 - loss: 3.4900
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m315/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.0728 - loss: 3.3530
[1m317/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.0728 - loss: 3.3528
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.0639 - loss: 3.4896
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.0640 - loss: 3.4892
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m319/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.0728 - loss: 3.3526
[1m321/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.0729 - loss: 3.3523
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.0641 - loss: 3.4888
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.0643 - loss: 3.4881
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m322/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.0729 - loss: 3.3522
[1m324/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0729 - loss: 3.3520
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 63ms/step - accuracy: 0.0644 - loss: 3.4878
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 63ms/step - accuracy: 0.0645 - loss: 3.4875
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m326/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0729 - loss: 3.3518
[1m328/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0730 - loss: 3.3516
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.0646 - loss: 3.4872
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.0647 - loss: 3.4870
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m330/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0730 - loss: 3.3513
[1m332/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0730 - loss: 3.3511
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 63ms/step - accuracy: 0.0648 - loss: 3.4867
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 63ms/step - accuracy: 0.0649 - loss: 3.4864
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m333/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0730 - loss: 3.3510
[1m335/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0731 - loss: 3.3508
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 63ms/step - accuracy: 0.0650 - loss: 3.4861
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 63ms/step - accuracy: 0.0651 - loss: 3.4858
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m337/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0731 - loss: 3.3506
[1m339/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0731 - loss: 3.3504
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.0652 - loss: 3.4855
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 63ms/step - accuracy: 0.0653 - loss: 3.4852
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m341/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0731 - loss: 3.3502
[1m343/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0732 - loss: 3.3500
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 63ms/step - accuracy: 0.0654 - loss: 3.4850
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 63ms/step - accuracy: 0.0655 - loss: 3.4846
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.0635 - loss: 3.4913[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m346/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0732 - loss: 3.3497
[1m348/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0732 - loss: 3.3495
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 64ms/step - accuracy: 0.0656 - loss: 3.4843
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 63ms/step - accuracy: 0.0657 - loss: 3.4839
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m350/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0733 - loss: 3.3493
[1m352/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0733 - loss: 3.3491
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 63ms/step - accuracy: 0.0658 - loss: 3.4836
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 63ms/step - accuracy: 0.0659 - loss: 3.4832
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m354/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0733 - loss: 3.3489
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 63ms/step - accuracy: 0.0660 - loss: 3.4829
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 63ms/step - accuracy: 0.0662 - loss: 3.4822
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m356/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.0733 - loss: 3.3487
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m358/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0734 - loss: 3.3485
[1m361/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0734 - loss: 3.3482
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m363/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0734 - loss: 3.3481
[1m365/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0734 - loss: 3.3479
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 63ms/step - accuracy: 0.0665 - loss: 3.4811
[1m 140/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 63ms/step - accuracy: 0.0666 - loss: 3.4808
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m367/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0735 - loss: 3.3477
[1m369/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0735 - loss: 3.3475
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 141/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 63ms/step - accuracy: 0.0667 - loss: 3.4805
[1m 142/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 63ms/step - accuracy: 0.0668 - loss: 3.4803
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m372/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0735 - loss: 3.3472
[1m374/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0735 - loss: 3.3470
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 63ms/step - accuracy: 0.0669 - loss: 3.4800
[1m 144/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 63ms/step - accuracy: 0.0669 - loss: 3.4798
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0736 - loss: 3.3469
[1m378/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0736 - loss: 3.3467
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 146/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0671 - loss: 3.4793
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 62ms/step - accuracy: 0.0671 - loss: 3.4790
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m380/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0736 - loss: 3.3465
[1m383/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0736 - loss: 3.3462
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m385/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0737 - loss: 3.3460
[1m387/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.0737 - loss: 3.3459
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m389/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.0737 - loss: 3.3457
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0674 - loss: 3.4781
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0674 - loss: 3.4778
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m391/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.0737 - loss: 3.3455
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m393/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.0737 - loss: 3.3453
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0675 - loss: 3.4776
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0675 - loss: 3.4774
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m395/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.0738 - loss: 3.3451
[1m397/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.0738 - loss: 3.3449
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m331/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1045 - loss: 3.0025
[1m333/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1046 - loss: 3.0016
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m399/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.0738 - loss: 3.3448
[1m401/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.0738 - loss: 3.3446
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0677 - loss: 3.4768
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0678 - loss: 3.4767
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m403/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.0738 - loss: 3.3444
[1m405/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.0738 - loss: 3.3442
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0680 - loss: 3.4761
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0680 - loss: 3.4758
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m346/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1052 - loss: 2.9959[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0681 - loss: 3.4754
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0682 - loss: 3.4752
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0683 - loss: 3.4750
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.0683 - loss: 3.4748
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 63ms/step - accuracy: 0.0684 - loss: 3.4745
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 63ms/step - accuracy: 0.0685 - loss: 3.4743
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 170/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 63ms/step - accuracy: 0.0685 - loss: 3.4741
[1m 171/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 63ms/step - accuracy: 0.0686 - loss: 3.4738
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 172/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 63ms/step - accuracy: 0.0687 - loss: 3.4736
[1m 173/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 63ms/step - accuracy: 0.0687 - loss: 3.4733
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 26ms/step - accuracy: 0.0665 - loss: 3.3716
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 26ms/step - accuracy: 0.0665 - loss: 3.3714
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 26ms/step - accuracy: 0.0665 - loss: 3.3713
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m31s[0m 38ms/step - accuracy: 0.0838 - loss: 3.1467
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m31s[0m 38ms/step - accuracy: 0.0838 - loss: 3.1465[32m [repeated 220x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0691 - loss: 3.4720
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0691 - loss: 3.4717
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0693 - loss: 3.4712
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0693 - loss: 3.4710
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m28s[0m 37ms/step - accuracy: 0.0889 - loss: 3.1052[32m [repeated 273x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0694 - loss: 3.4704
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0695 - loss: 3.4702
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0696 - loss: 3.4700
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0696 - loss: 3.4697
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0697 - loss: 3.4695
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0697 - loss: 3.4693
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0699 - loss: 3.4687
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 63ms/step - accuracy: 0.0699 - loss: 3.4685
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m178/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 64ms/step - accuracy: 0.0739 - loss: 3.3929
[1m179/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 64ms/step - accuracy: 0.0740 - loss: 3.3924[32m [repeated 145x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m185/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m26s[0m 65ms/step - accuracy: 0.0852 - loss: 3.3153[32m [repeated 210x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 63ms/step - accuracy: 0.0705 - loss: 3.4663
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 63ms/step - accuracy: 0.0705 - loss: 3.4661
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 63ms/step - accuracy: 0.0706 - loss: 3.4659
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 62ms/step - accuracy: 0.0706 - loss: 3.4657
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 62ms/step - accuracy: 0.0707 - loss: 3.4653 
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 62ms/step - accuracy: 0.0708 - loss: 3.4651
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 63ms/step - accuracy: 0.0703 - loss: 3.4667[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m202/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 65ms/step - accuracy: 0.0865 - loss: 3.3030
[1m203/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 65ms/step - accuracy: 0.0866 - loss: 3.3023
[1m204/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 65ms/step - accuracy: 0.0867 - loss: 3.3016
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m364/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.0726 - loss: 3.3382 
[1m366/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.0726 - loss: 3.3380
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m368/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.0726 - loss: 3.3379
[1m369/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.0726 - loss: 3.3378[32m [repeated 62x across cluster][0m

Trial status: 20 RUNNING
Current time: 2025-10-31 15:05:10. Total running time: 30s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m461/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 40ms/step - accuracy: 0.1107 - loss: 2.9499[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m243/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m22s[0m 65ms/step - accuracy: 0.0892 - loss: 3.2761
[1m244/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m22s[0m 65ms/step - accuracy: 0.0893 - loss: 3.2755
[1m245/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 65ms/step - accuracy: 0.0894 - loss: 3.2749
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m57s[0m 62ms/step - accuracy: 0.0724 - loss: 3.4596
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m57s[0m 62ms/step - accuracy: 0.0725 - loss: 3.4595
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m57s[0m 62ms/step - accuracy: 0.0725 - loss: 3.4593[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 37ms/step - accuracy: 0.0894 - loss: 3.1646
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 37ms/step - accuracy: 0.0894 - loss: 3.1643[32m [repeated 252x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0722 - loss: 3.3257 
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0722 - loss: 3.3255
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0722 - loss: 3.3253
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0722 - loss: 3.3251
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m26s[0m 38ms/step - accuracy: 0.0868 - loss: 3.1224[32m [repeated 254x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0722 - loss: 3.3249
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0722 - loss: 3.3248
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0723 - loss: 3.3245
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0723 - loss: 3.3243
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0723 - loss: 3.3241
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0723 - loss: 3.3239
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0723 - loss: 3.3238
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0723 - loss: 3.3235
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0723 - loss: 3.3234
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0724 - loss: 3.3231
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m265/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 64ms/step - accuracy: 0.0905 - loss: 3.2634
[1m266/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 64ms/step - accuracy: 0.0905 - loss: 3.2628[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m342/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 59ms/step - accuracy: 0.0726 - loss: 3.3461[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0724 - loss: 3.3230
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.0724 - loss: 3.3227
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.0724 - loss: 3.3225
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.0724 - loss: 3.3223
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.0724 - loss: 3.3222
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.0725 - loss: 3.3220
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.0725 - loss: 3.3218
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.0725 - loss: 3.3216
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.0725 - loss: 3.3213
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.0725 - loss: 3.3212
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.0725 - loss: 3.3209
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.0726 - loss: 3.3207
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 37ms/step - accuracy: 0.0749 - loss: 3.3282 - val_accuracy: 0.1058 - val_loss: 2.8272
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m301/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 63ms/step - accuracy: 0.0924 - loss: 3.2439
[1m302/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 63ms/step - accuracy: 0.0924 - loss: 3.2433
[1m303/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 63ms/step - accuracy: 0.0925 - loss: 3.2428
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 2/29
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 114ms/step - accuracy: 0.0000e+00 - loss: 3.2501
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 40ms/step - accuracy: 0.0295 - loss: 3.2117      
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m548/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 40ms/step - accuracy: 0.0698 - loss: 3.3967
[1m550/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 40ms/step - accuracy: 0.0698 - loss: 3.3964[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m495/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 45ms/step - accuracy: 0.0738 - loss: 3.3291[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 28ms/step - accuracy: 0.0659 - loss: 3.3411
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 28ms/step - accuracy: 0.0659 - loss: 3.3410
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 28ms/step - accuracy: 0.0659 - loss: 3.3408[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.0949 - loss: 3.1878
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.0949 - loss: 3.1873[32m [repeated 208x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.0661 - loss: 3.3362 
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.0662 - loss: 3.3360
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.0703 - loss: 3.3282
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.0703 - loss: 3.3278[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m50s[0m 62ms/step - accuracy: 0.0758 - loss: 3.4440[32m [repeated 223x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.0664 - loss: 3.3299[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m350/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 63ms/step - accuracy: 0.0946 - loss: 3.2205
[1m351/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 63ms/step - accuracy: 0.0946 - loss: 3.2201[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m336/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 64ms/step - accuracy: 0.0804 - loss: 3.3374[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m434/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 53ms/step - accuracy: 0.0632 - loss: 3.4687
[1m435/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 53ms/step - accuracy: 0.0632 - loss: 3.4686
[1m436/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 53ms/step - accuracy: 0.0632 - loss: 3.4686
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m358/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 64ms/step - accuracy: 0.0812 - loss: 3.3311
[1m359/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 64ms/step - accuracy: 0.0812 - loss: 3.3309
[1m360/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 64ms/step - accuracy: 0.0813 - loss: 3.3306
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 48ms/step - accuracy: 0.1161 - loss: 2.9081 - val_accuracy: 0.1863 - val_loss: 2.2436
[36m(train_cnn_ray_tune pid=1593422)[0m Epoch 2/29
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m463/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 53ms/step - accuracy: 0.0634 - loss: 3.4673
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 53ms/step - accuracy: 0.0634 - loss: 3.4673[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.1562 - loss: 2.5698
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 50ms/step - accuracy: 0.1797 - loss: 2.5351
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m471/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 60ms/step - accuracy: 0.0748 - loss: 3.3208[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 123ms/step - accuracy: 0.0625 - loss: 3.3502
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 52ms/step - accuracy: 0.0781 - loss: 3.3107  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 52ms/step - accuracy: 0.0868 - loss: 3.2890
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 37ms/step - accuracy: 0.0987 - loss: 3.1581
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 37ms/step - accuracy: 0.0987 - loss: 3.1576[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m424/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 62ms/step - accuracy: 0.0978 - loss: 3.1889 
[1m425/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 62ms/step - accuracy: 0.0979 - loss: 3.1885
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 26ms/step - accuracy: 0.0720 - loss: 3.3077
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 26ms/step - accuracy: 0.0721 - loss: 3.3074[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 27ms/step - accuracy: 0.0674 - loss: 3.3121
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 27ms/step - accuracy: 0.0674 - loss: 3.3119
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.0674 - loss: 3.3117
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m16s[0m 38ms/step - accuracy: 0.0921 - loss: 3.0836[32m [repeated 228x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.0721 - loss: 3.3068[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 41ms/step - accuracy: 0.1508 - loss: 2.5358
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 41ms/step - accuracy: 0.1509 - loss: 2.5349[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 36/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 41ms/step - accuracy: 0.0967 - loss: 3.1752[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m45s[0m 62ms/step - accuracy: 0.0780 - loss: 3.4316
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m45s[0m 62ms/step - accuracy: 0.0780 - loss: 3.4314
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m45s[0m 62ms/step - accuracy: 0.0780 - loss: 3.4313
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.0988 - loss: 3.1048 
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.0989 - loss: 3.1045
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 52ms/step - accuracy: 0.0745 - loss: 3.3239 - val_accuracy: 0.1008 - val_loss: 2.7444[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 2/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m482/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 62ms/step - accuracy: 0.1003 - loss: 3.1665
[1m483/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 62ms/step - accuracy: 0.1003 - loss: 3.1662[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m493/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 62ms/step - accuracy: 0.1007 - loss: 3.1625[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 123ms/step - accuracy: 0.1562 - loss: 3.3410
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 38ms/step - accuracy: 0.0941 - loss: 3.0679
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 38ms/step - accuracy: 0.0941 - loss: 3.0676[32m [repeated 142x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m427/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 64ms/step - accuracy: 0.0838 - loss: 3.3129 
[1m428/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 64ms/step - accuracy: 0.0839 - loss: 3.3126
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.1001 - loss: 3.0971
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.1001 - loss: 3.0969[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.0943 - loss: 3.0664[32m [repeated 183x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1027 - loss: 3.1274[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 31ms/step - accuracy: 0.0750 - loss: 3.2942 - val_accuracy: 0.1297 - val_loss: 2.7022
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:12[0m 113ms/step - accuracy: 0.0000e+00 - loss: 3.2304
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 54ms/step - accuracy: 0.0156 - loss: 3.0854     
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.0208 - loss: 3.0921 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.0330 - loss: 3.1118
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 74/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 43ms/step - accuracy: 0.0855 - loss: 3.2621
[1m 76/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 43ms/step - accuracy: 0.0856 - loss: 3.2612[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m162/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m16s[0m 40ms/step - accuracy: 0.0978 - loss: 3.1530[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.0983 - loss: 3.1079
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.0983 - loss: 3.1078
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.0984 - loss: 3.1075
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:30[0m 77ms/step - accuracy: 0.0625 - loss: 2.9088
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.0947 - loss: 3.0633 
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.0947 - loss: 3.0631[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.1562 - loss: 3.1100 
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 59ms/step - accuracy: 0.1229 - loss: 2.8635 - val_accuracy: 0.1804 - val_loss: 2.2464
[36m(train_cnn_ray_tune pid=1593431)[0m Epoch 2/18[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m576/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 61ms/step - accuracy: 0.1039 - loss: 3.1337
[1m577/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 61ms/step - accuracy: 0.1040 - loss: 3.1334[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 61ms/step - accuracy: 0.1042 - loss: 3.1311[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 25ms/step - accuracy: 0.0999 - loss: 2.9839
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 25ms/step - accuracy: 0.0999 - loss: 2.9837
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 25ms/step - accuracy: 0.0999 - loss: 2.9837
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 61ms/step - accuracy: 0.0641 - loss: 3.4604 - val_accuracy: 0.0592 - val_loss: 2.9716
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m34s[0m 60ms/step - accuracy: 0.0803 - loss: 3.4140
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m34s[0m 60ms/step - accuracy: 0.0803 - loss: 3.4139[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 36ms/step - accuracy: 0.1060 - loss: 3.1030
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 36ms/step - accuracy: 0.1060 - loss: 3.1027[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 40ms/step - accuracy: 0.0950 - loss: 3.0647[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 34ms/step - accuracy: 0.0801 - loss: 3.2351
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 34ms/step - accuracy: 0.0801 - loss: 3.2350
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 34ms/step - accuracy: 0.0801 - loss: 3.2349
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 36ms/step - accuracy: 0.1033 - loss: 3.0760[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 31ms/step - accuracy: 0.0681 - loss: 3.3013 - val_accuracy: 0.0727 - val_loss: 2.6803[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:34[0m 162ms/step - accuracy: 0.1875 - loss: 2.6150
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.1797 - loss: 2.6081  
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.0911 - loss: 2.9696 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.0922 - loss: 2.9509
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m290/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 39ms/step - accuracy: 0.1000 - loss: 3.1451
[1m292/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 39ms/step - accuracy: 0.1000 - loss: 3.1450[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m208/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m15s[0m 40ms/step - accuracy: 0.0890 - loss: 3.2289[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 82ms/step - accuracy: 0.0625 - loss: 3.1821[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m331/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1607 - loss: 2.4795 
[1m333/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1607 - loss: 2.4793
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 3/29[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m378/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 38ms/step - accuracy: 0.1014 - loss: 3.1397
[1m380/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 38ms/step - accuracy: 0.1014 - loss: 3.1396[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m390/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 38ms/step - accuracy: 0.1015 - loss: 3.1392[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 69ms/step - accuracy: 0.1043 - loss: 3.1308 - val_accuracy: 0.1817 - val_loss: 2.3773[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m10s[0m 46ms/step - accuracy: 0.1104 - loss: 2.9548
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m10s[0m 46ms/step - accuracy: 0.1104 - loss: 2.9543[32m [repeated 141x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.1106 - loss: 2.9524
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.1107 - loss: 2.9520[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m20s[0m 24ms/step - accuracy: 0.0828 - loss: 3.0200[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 39ms/step - accuracy: 0.0979 - loss: 3.0348
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 39ms/step - accuracy: 0.0979 - loss: 3.0344
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 39ms/step - accuracy: 0.0980 - loss: 3.0340
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 39ms/step - accuracy: 0.0981 - loss: 3.0328[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m26s[0m 59ms/step - accuracy: 0.0819 - loss: 3.4004
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m26s[0m 59ms/step - accuracy: 0.0819 - loss: 3.4003
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m26s[0m 59ms/step - accuracy: 0.0819 - loss: 3.4002
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m216/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 45ms/step - accuracy: 0.1728 - loss: 2.4471
[1m217/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 45ms/step - accuracy: 0.1728 - loss: 2.4470[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 36/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 49ms/step - accuracy: 0.1562 - loss: 2.6874[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 57ms/step - accuracy: 0.1059 - loss: 3.0519  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 50ms/step - accuracy: 0.1251 - loss: 3.0240
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 142ms/step - accuracy: 0.0625 - loss: 3.0822[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m323/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.0906 - loss: 3.2164 
[1m325/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.0906 - loss: 3.2162[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m50s[0m 39ms/step - accuracy: 0.0803 - loss: 3.2328 - val_accuracy: 0.1308 - val_loss: 2.6247
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.2604 - loss: 2.7971  
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.2917 - loss: 2.3685 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 30ms/step - accuracy: 0.2606 - loss: 2.4344
[36m(train_cnn_ray_tune pid=1593435)[0m Epoch 2/17[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m529/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 37ms/step - accuracy: 0.1028 - loss: 3.1319
[1m531/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 37ms/step - accuracy: 0.1028 - loss: 3.1318[32m [repeated 76x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-10-31 15:05:40. Total running time: 1min 0s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m541/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 37ms/step - accuracy: 0.1029 - loss: 3.1314[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 71ms/step - accuracy: 0.0892 - loss: 3.2753 - val_accuracy: 0.1743 - val_loss: 2.5037
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 35ms/step - accuracy: 0.2125 - loss: 2.5176
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 35ms/step - accuracy: 0.2116 - loss: 2.5218[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:50[0m 95ms/step - accuracy: 0.3125 - loss: 2.3355
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 38ms/step - accuracy: 0.2743 - loss: 2.3050 
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 45ms/step - accuracy: 0.1133 - loss: 2.9268
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 45ms/step - accuracy: 0.1134 - loss: 2.9264[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.2108 - loss: 2.4151[32m [repeated 132x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 45ms/step - accuracy: 0.1137 - loss: 2.9237[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.1667 - loss: 2.8063 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 58ms/step - accuracy: 0.0829 - loss: 3.3915
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 58ms/step - accuracy: 0.0829 - loss: 3.3914
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 58ms/step - accuracy: 0.0829 - loss: 3.3913[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 98/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 53ms/step - accuracy: 0.1387 - loss: 2.9478
[1m 99/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 53ms/step - accuracy: 0.1387 - loss: 2.9478[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m133/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.1616 - loss: 2.6850[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:36[0m 83ms/step - accuracy: 0.1875 - loss: 2.9329[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m169/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.0954 - loss: 3.0618 
[1m171/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.0953 - loss: 3.0619
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m53s[0m 41ms/step - accuracy: 0.0984 - loss: 3.0343 - val_accuracy: 0.1650 - val_loss: 2.4065[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.0984 - loss: 2.9970 
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.0984 - loss: 2.9969
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.1661 - loss: 2.4540 - val_accuracy: 0.2141 - val_loss: 2.1068
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.1701 - loss: 2.6404 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.1877 - loss: 2.5870
[36m(train_cnn_ray_tune pid=1593440)[0m Epoch 3/16[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m577/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.0918 - loss: 3.2041
[1m579/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.0918 - loss: 3.2040[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m583/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.0918 - loss: 3.2039[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 144/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 33ms/step - accuracy: 0.1694 - loss: 2.5929
[1m 146/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 33ms/step - accuracy: 0.1694 - loss: 2.5928[32m [repeated 200x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 84ms/step - accuracy: 0.1250 - loss: 2.7823
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 38ms/step - accuracy: 0.1424 - loss: 2.9237[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m354/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.0701 - loss: 3.3115 
[1m356/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.0702 - loss: 3.3114
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.1051 - loss: 2.9520
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.1051 - loss: 2.9519[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 30ms/step - accuracy: 0.1016 - loss: 3.0510[32m [repeated 230x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.0988 - loss: 2.9943[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 34ms/step - accuracy: 0.1912 - loss: 2.6052
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 34ms/step - accuracy: 0.1910 - loss: 2.6054
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 33ms/step - accuracy: 0.1908 - loss: 2.6056[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 67/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 34ms/step - accuracy: 0.1212 - loss: 2.9841
[1m 69/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 34ms/step - accuracy: 0.1209 - loss: 2.9855[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m225/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 52ms/step - accuracy: 0.1646 - loss: 2.6740[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m58s[0m 44ms/step - accuracy: 0.1002 - loss: 3.0120 - val_accuracy: 0.1639 - val_loss: 2.3233
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 119ms/step - accuracy: 0.1875 - loss: 2.8549
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.0992 - loss: 2.9907
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.0992 - loss: 2.9907
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.0992 - loss: 2.9906
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m119/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 39ms/step - accuracy: 0.1844 - loss: 2.3066
[1m121/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 39ms/step - accuracy: 0.1846 - loss: 2.3066
[1m122/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 39ms/step - accuracy: 0.1847 - loss: 2.3066
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 42ms/step - accuracy: 0.0918 - loss: 3.2038 - val_accuracy: 0.1386 - val_loss: 2.6663[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 3/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m503/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 45ms/step - accuracy: 0.1772 - loss: 2.4181
[1m504/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 45ms/step - accuracy: 0.1772 - loss: 2.4180[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m436/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 44ms/step - accuracy: 0.0711 - loss: 3.3067[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 57ms/step - accuracy: 0.0856 - loss: 3.3677 
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 57ms/step - accuracy: 0.0856 - loss: 3.3676
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m31s[0m 35ms/step - accuracy: 0.1191 - loss: 2.7805
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m31s[0m 35ms/step - accuracy: 0.1191 - loss: 2.7804[32m [repeated 176x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:50[0m 94ms/step - accuracy: 0.2500 - loss: 2.1961
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.1979 - loss: 2.4599 
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 24ms/step - accuracy: 0.1054 - loss: 2.9436
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 24ms/step - accuracy: 0.1054 - loss: 2.9435[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m31s[0m 35ms/step - accuracy: 0.1191 - loss: 2.7799[32m [repeated 161x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 24ms/step - accuracy: 0.1055 - loss: 2.9429[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 34ms/step - accuracy: 0.1698 - loss: 2.5858
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 34ms/step - accuracy: 0.1698 - loss: 2.5857
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m29s[0m 34ms/step - accuracy: 0.1698 - loss: 2.5856
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m209/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.1187 - loss: 3.0000
[1m211/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.1187 - loss: 2.9999[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m284/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 54ms/step - accuracy: 0.1380 - loss: 2.9354[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 98ms/step - accuracy: 0.0938 - loss: 2.7743
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 29ms/step - accuracy: 0.1146 - loss: 2.8070
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m64s[0m 51ms/step - accuracy: 0.1155 - loss: 2.9061 - val_accuracy: 0.1998 - val_loss: 2.1382
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 40ms/step - accuracy: 0.2118 - loss: 2.3739  
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:16[0m 117ms/step - accuracy: 0.2500 - loss: 2.4314
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 30ms/step - accuracy: 0.1011 - loss: 3.0326
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 30ms/step - accuracy: 0.1011 - loss: 3.0325
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 30ms/step - accuracy: 0.1011 - loss: 3.0324
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 56ms/step - accuracy: 0.0860 - loss: 3.3637
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 56ms/step - accuracy: 0.0860 - loss: 3.3636
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 56ms/step - accuracy: 0.0860 - loss: 3.3635
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 31ms/step - accuracy: 0.0922 - loss: 3.0533 - val_accuracy: 0.1451 - val_loss: 2.6862
[36m(train_cnn_ray_tune pid=1593442)[0m Epoch 2/22[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m532/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 45ms/step - accuracy: 0.0722 - loss: 3.3008
[1m533/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 45ms/step - accuracy: 0.0722 - loss: 3.3007[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m544/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 45ms/step - accuracy: 0.0724 - loss: 3.3001[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m307/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1197 - loss: 2.9973 
[1m309/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1197 - loss: 2.9973
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m24s[0m 34ms/step - accuracy: 0.1718 - loss: 2.5781
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m24s[0m 34ms/step - accuracy: 0.1718 - loss: 2.5780[32m [repeated 160x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 56ms/step - accuracy: 0.0868 - loss: 3.3566
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 56ms/step - accuracy: 0.0868 - loss: 3.3565[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m22s[0m 34ms/step - accuracy: 0.1774 - loss: 2.6143[32m [repeated 180x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 56ms/step - accuracy: 0.0869 - loss: 3.3557[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m374/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 54ms/step - accuracy: 0.1388 - loss: 2.9272
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 54ms/step - accuracy: 0.1389 - loss: 2.9270[32m [repeated 131x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m175/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 29ms/step - accuracy: 0.1011 - loss: 2.9432[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 52ms/step - accuracy: 0.1783 - loss: 2.4112 - val_accuracy: 0.2155 - val_loss: 2.0742
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 136ms/step - accuracy: 0.3125 - loss: 2.1249
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 64ms/step - accuracy: 0.2656 - loss: 2.1780  
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 27ms/step - accuracy: 0.1000 - loss: 2.9829 - val_accuracy: 0.1571 - val_loss: 2.5966
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:04[0m 107ms/step - accuracy: 0.1250 - loss: 2.9210
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1424 - loss: 2.9017  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.1548 - loss: 2.8813
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m417/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1211 - loss: 2.9913
[1m418/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1211 - loss: 2.9912
[1m419/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1211 - loss: 2.9912
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1250 - loss: 2.9189 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1169 - loss: 2.8955
[36m(train_cnn_ray_tune pid=1593429)[0m Epoch 3/15[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m458/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 54ms/step - accuracy: 0.1684 - loss: 2.6564
[1m459/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 54ms/step - accuracy: 0.1684 - loss: 2.6563[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 34ms/step - accuracy: 0.1734 - loss: 2.5716
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 34ms/step - accuracy: 0.1734 - loss: 2.5714
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 34ms/step - accuracy: 0.1735 - loss: 2.5713
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m435/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1213 - loss: 2.9904[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 34ms/step - accuracy: 0.1206 - loss: 2.7649
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 34ms/step - accuracy: 0.1206 - loss: 2.7648[32m [repeated 193x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 56ms/step - accuracy: 0.0875 - loss: 3.3503
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 56ms/step - accuracy: 0.0875 - loss: 3.3502[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.1739 - loss: 2.5689[32m [repeated 160x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 56ms/step - accuracy: 0.0875 - loss: 3.3496[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 39/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 44ms/step - accuracy: 0.1130 - loss: 3.1390
[1m 41/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.1118 - loss: 3.1406[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m107/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m20s[0m 44ms/step - accuracy: 0.2026 - loss: 2.2168[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 51ms/step - accuracy: 0.0728 - loss: 3.2979 - val_accuracy: 0.0862 - val_loss: 2.8708
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 128ms/step - accuracy: 0.0938 - loss: 3.3009
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 42ms/step - accuracy: 0.1215 - loss: 3.1113  
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1018 - loss: 3.0199 
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1018 - loss: 3.0198
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 28ms/step - accuracy: 0.0916 - loss: 2.9537 - val_accuracy: 0.1112 - val_loss: 2.5434[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.0625 - loss: 3.2296[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 18ms/step - accuracy: 0.0625 - loss: 3.0610 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.0698 - loss: 3.0159
[36m(train_cnn_ray_tune pid=1593431)[0m Epoch 3/18[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m575/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1224 - loss: 2.9846
[1m577/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1224 - loss: 2.9845[32m [repeated 155x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.1015 - loss: 3.0235
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.1015 - loss: 3.0235
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.1015 - loss: 3.0234
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m568/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 53ms/step - accuracy: 0.1690 - loss: 2.6498[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 34ms/step - accuracy: 0.1224 - loss: 2.7571
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 34ms/step - accuracy: 0.1224 - loss: 2.7570[32m [repeated 267x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.1023 - loss: 3.0148
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.1024 - loss: 3.0147[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m33s[0m 40ms/step - accuracy: 0.1738 - loss: 2.4008[32m [repeated 186x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1024 - loss: 3.0141[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m151/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 44ms/step - accuracy: 0.0928 - loss: 3.1725
[1m153/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 44ms/step - accuracy: 0.0928 - loss: 3.1725[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m155/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 44ms/step - accuracy: 0.0927 - loss: 3.1725[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m579/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 53ms/step - accuracy: 0.1405 - loss: 2.9135
[1m580/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 53ms/step - accuracy: 0.1405 - loss: 2.9134
[1m581/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 53ms/step - accuracy: 0.1406 - loss: 2.9133
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.1225 - loss: 2.9842 - val_accuracy: 0.1711 - val_loss: 2.4722
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1752 - loss: 2.6046 
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1752 - loss: 2.6046
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 82ms/step - accuracy: 0.0625 - loss: 2.9461
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.0590 - loss: 2.9863
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m185/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 43ms/step - accuracy: 0.0924 - loss: 3.1714
[1m187/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 43ms/step - accuracy: 0.0924 - loss: 3.1713
[1m189/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m16s[0m 43ms/step - accuracy: 0.0924 - loss: 3.1712
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 79ms/step - accuracy: 0.2188 - loss: 2.3406
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m81s[0m 64ms/step - accuracy: 0.0875 - loss: 3.3495 - val_accuracy: 0.1358 - val_loss: 2.6335
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 51ms/step - accuracy: 0.1227 - loss: 3.0106 
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1757 - loss: 2.5551
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1757 - loss: 2.5550
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1757 - loss: 2.5549
Trial status: 20 RUNNING
Current time: 2025-10-31 15:06:10. Total running time: 1min 30s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593444)[0m Epoch 3/23[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m581/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.1011 - loss: 3.1251
[1m583/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.1011 - loss: 3.1251[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m575/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.1011 - loss: 3.1252[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 22ms/step - accuracy: 0.1130 - loss: 2.8159
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 22ms/step - accuracy: 0.1130 - loss: 2.8158[32m [repeated 213x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.1761 - loss: 2.5520
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.1761 - loss: 2.5519[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 49ms/step - accuracy: 0.1004 - loss: 3.0843[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 59ms/step - accuracy: 0.1016 - loss: 3.0592  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 56ms/step - accuracy: 0.1059 - loss: 3.0080
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 29ms/step - accuracy: 0.1033 - loss: 3.0066[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 49ms/step - accuracy: 0.0994 - loss: 3.0887
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 49ms/step - accuracy: 0.0993 - loss: 3.0894
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 49ms/step - accuracy: 0.0991 - loss: 3.0901
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m141/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 32ms/step - accuracy: 0.1284 - loss: 2.9204
[1m143/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 32ms/step - accuracy: 0.1285 - loss: 2.9200[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 46/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 50ms/step - accuracy: 0.1918 - loss: 2.5357[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 60ms/step - accuracy: 0.1406 - loss: 2.9131 - val_accuracy: 0.1835 - val_loss: 2.3880[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:17[0m 118ms/step - accuracy: 0.1250 - loss: 2.8366
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 48ms/step - accuracy: 0.1250 - loss: 3.0357  
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 50ms/step - accuracy: 0.0975 - loss: 3.0961
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 50ms/step - accuracy: 0.0975 - loss: 3.0963
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 50ms/step - accuracy: 0.0975 - loss: 3.0964
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 95ms/step - accuracy: 0.0312 - loss: 3.2989
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 61ms/step - accuracy: 0.0547 - loss: 3.3088
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6:36:32[0m 41s/step - accuracy: 0.0625 - loss: 3.1326[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 53ms/step - accuracy: 0.1016 - loss: 3.0791   
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 4/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m388/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 44ms/step - accuracy: 0.2050 - loss: 2.2305
[1m389/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 44ms/step - accuracy: 0.2050 - loss: 2.2305[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m398/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 45ms/step - accuracy: 0.2050 - loss: 2.2306[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 52ms/step - accuracy: 0.0969 - loss: 3.0945
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 52ms/step - accuracy: 0.0970 - loss: 3.0943
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 52ms/step - accuracy: 0.0970 - loss: 3.0942
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m24s[0m 41ms/step - accuracy: 0.1737 - loss: 2.3965
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m24s[0m 41ms/step - accuracy: 0.1737 - loss: 2.3965[32m [repeated 154x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m360/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.0910 - loss: 3.1651 
[1m361/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.0910 - loss: 3.1651
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 33ms/step - accuracy: 0.1261 - loss: 2.7404
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 33ms/step - accuracy: 0.1261 - loss: 2.7404[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.1738 - loss: 2.3961[32m [repeated 149x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 33ms/step - accuracy: 0.1893 - loss: 2.3354[32m [repeated 89x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 33ms/step - accuracy: 0.1033 - loss: 3.0065 - val_accuracy: 0.1360 - val_loss: 2.5317
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 45ms/step - accuracy: 0.0556 - loss: 2.7906  
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 97/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m28s[0m 58ms/step - accuracy: 0.1565 - loss: 2.8093
[1m 98/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m28s[0m 58ms/step - accuracy: 0.1566 - loss: 2.8090[32m [repeated 153x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m135/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m24s[0m 55ms/step - accuracy: 0.1891 - loss: 2.5257[32m [repeated 210x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 42ms/step - accuracy: 0.1011 - loss: 3.1251 - val_accuracy: 0.1582 - val_loss: 2.6142
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:08[0m 110ms/step - accuracy: 0.0625 - loss: 2.7296
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m101/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 60ms/step - accuracy: 0.1104 - loss: 2.9908
[1m102/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m28s[0m 60ms/step - accuracy: 0.1104 - loss: 2.9910
[1m103/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m28s[0m 60ms/step - accuracy: 0.1104 - loss: 2.9912
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 3/27
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m333/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1341 - loss: 2.9016
[1m334/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1341 - loss: 2.9015[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m433/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 47ms/step - accuracy: 0.0911 - loss: 3.1625[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 34ms/step - accuracy: 0.0958 - loss: 2.9333
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 34ms/step - accuracy: 0.0960 - loss: 2.9330[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m313/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1338 - loss: 2.9027 
[1m315/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1338 - loss: 2.9026
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 24ms/step - accuracy: 0.1148 - loss: 2.7990
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 24ms/step - accuracy: 0.1148 - loss: 2.7988[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 35ms/step - accuracy: 0.0973 - loss: 2.9314[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m330/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2370 - loss: 2.1632 
[1m332/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2371 - loss: 2.1632
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m20s[0m 42ms/step - accuracy: 0.1745 - loss: 2.3910
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m20s[0m 42ms/step - accuracy: 0.1745 - loss: 2.3910
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m20s[0m 42ms/step - accuracy: 0.1745 - loss: 2.3909
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 25ms/step - accuracy: 0.1136 - loss: 2.8308[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m212/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 59ms/step - accuracy: 0.1907 - loss: 2.5157
[1m213/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 59ms/step - accuracy: 0.1907 - loss: 2.5156[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m188/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 58ms/step - accuracy: 0.1609 - loss: 2.7942[32m [repeated 157x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 37ms/step - accuracy: 0.1749 - loss: 2.5944 - val_accuracy: 0.2044 - val_loss: 2.2510
[36m(train_cnn_ray_tune pid=1593435)[0m Epoch 3/17
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 82ms/step - accuracy: 0.1250 - loss: 2.7119
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 29ms/step - accuracy: 0.1319 - loss: 2.6319 
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m174/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 58ms/step - accuracy: 0.1087 - loss: 2.9916
[1m175/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 58ms/step - accuracy: 0.1087 - loss: 2.9914
[1m176/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 58ms/step - accuracy: 0.1087 - loss: 2.9913
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m460/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.1352 - loss: 2.8972
[1m462/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.1352 - loss: 2.8971[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m423/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 40ms/step - accuracy: 0.2376 - loss: 2.1599[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 34ms/step - accuracy: 0.2045 - loss: 2.4249
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 34ms/step - accuracy: 0.2044 - loss: 2.4248[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 38ms/step - accuracy: 0.2188 - loss: 2.4601 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.2181 - loss: 2.4504
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 24ms/step - accuracy: 0.1153 - loss: 2.7920
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 24ms/step - accuracy: 0.1153 - loss: 2.7920[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 35ms/step - accuracy: 0.2038 - loss: 2.4238[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 26ms/step - accuracy: 0.1154 - loss: 2.7799[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m343/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.1072 - loss: 3.0684 
[1m345/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.1072 - loss: 3.0683
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m295/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 59ms/step - accuracy: 0.1908 - loss: 2.5093
[1m296/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 59ms/step - accuracy: 0.1908 - loss: 2.5092[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m293/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 59ms/step - accuracy: 0.1908 - loss: 2.5094[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m45s[0m 38ms/step - accuracy: 0.1272 - loss: 2.7344 - val_accuracy: 0.1893 - val_loss: 2.3016[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 3/23[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:03[0m 106ms/step - accuracy: 0.2500 - loss: 2.5145
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 51ms/step - accuracy: 0.2344 - loss: 2.4789 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 54ms/step - accuracy: 0.2057 - loss: 2.2283 - val_accuracy: 0.2799 - val_loss: 2.0095
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 120ms/step - accuracy: 0.2500 - loss: 2.2301
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 55ms/step - accuracy: 0.2344 - loss: 2.2647  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.2305 - loss: 2.2741
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m341/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 58ms/step - accuracy: 0.1907 - loss: 2.5059
[1m342/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 58ms/step - accuracy: 0.1907 - loss: 2.5058
[1m343/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 58ms/step - accuracy: 0.1907 - loss: 2.5057
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m415/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 41ms/step - accuracy: 0.1079 - loss: 3.0644
[1m417/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 41ms/step - accuracy: 0.1079 - loss: 3.0643[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m429/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 41ms/step - accuracy: 0.1080 - loss: 3.0636[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 141/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 34ms/step - accuracy: 0.1612 - loss: 2.5966
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 34ms/step - accuracy: 0.1609 - loss: 2.5969[32m [repeated 142x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1632 - loss: 2.8123 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.1488 - loss: 2.7750
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.1157 - loss: 2.7754
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.1157 - loss: 2.7754[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 34ms/step - accuracy: 0.1599 - loss: 2.5978[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.1157 - loss: 2.7753[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m388/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 58ms/step - accuracy: 0.1908 - loss: 2.5032
[1m389/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 58ms/step - accuracy: 0.1908 - loss: 2.5031[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m329/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 58ms/step - accuracy: 0.1112 - loss: 2.9688[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 28ms/step - accuracy: 0.1155 - loss: 2.7901 - val_accuracy: 0.1512 - val_loss: 2.4182[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m Epoch 5/16[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46[0m 91ms/step - accuracy: 0.1250 - loss: 2.5767
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1120 - loss: 2.6530 
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 42ms/step - accuracy: 0.1357 - loss: 2.8936 - val_accuracy: 0.1734 - val_loss: 2.4230[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 128ms/step - accuracy: 0.2188 - loss: 2.5141[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m405/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.1638 - loss: 2.7713 
[1m406/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.1638 - loss: 2.7712
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 60ms/step - accuracy: 0.1406 - loss: 2.4377 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 64ms/step - accuracy: 0.1493 - loss: 2.4306
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.1590 - loss: 2.4049 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 44ms/step - accuracy: 0.1684 - loss: 2.3949
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 36/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.1475 - loss: 2.7977
[1m 37/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.1476 - loss: 2.7976
[1m 39/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.1477 - loss: 2.7976[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m422/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.1639 - loss: 2.7700
[1m423/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 56ms/step - accuracy: 0.1639 - loss: 2.7699[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m443/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 58ms/step - accuracy: 0.1908 - loss: 2.5002[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 34ms/step - accuracy: 0.1549 - loss: 2.5952
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 34ms/step - accuracy: 0.1549 - loss: 2.5952[32m [repeated 180x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 42ms/step - accuracy: 0.1778 - loss: 2.3732
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 42ms/step - accuracy: 0.1778 - loss: 2.3731[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m29s[0m 34ms/step - accuracy: 0.1546 - loss: 2.5948[32m [repeated 202x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 42ms/step - accuracy: 0.1779 - loss: 2.3728[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m35s[0m 55ms/step - accuracy: 0.1067 - loss: 3.0769
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m35s[0m 55ms/step - accuracy: 0.1067 - loss: 3.0768
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m35s[0m 55ms/step - accuracy: 0.1067 - loss: 3.0767
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m122/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 47ms/step - accuracy: 0.0990 - loss: 3.0733
[1m124/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 47ms/step - accuracy: 0.0991 - loss: 3.0736[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m186/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m18s[0m 47ms/step - accuracy: 0.2337 - loss: 2.1446[32m [repeated 163x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 29ms/step - accuracy: 0.1157 - loss: 2.7752 - val_accuracy: 0.1467 - val_loss: 2.4772[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m Epoch 4/18[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 45ms/step - accuracy: 0.2380 - loss: 2.1538 - val_accuracy: 0.2659 - val_loss: 1.9540
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:38[0m 84ms/step - accuracy: 0.1250 - loss: 2.6939[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m411/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1131 - loss: 2.9567 
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1132 - loss: 2.9565
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1029 - loss: 2.7120 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1033 - loss: 2.7137
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 45ms/step - accuracy: 0.1095 - loss: 3.0554 - val_accuracy: 0.1632 - val_loss: 2.5761
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 43ms/step - accuracy: 0.1783 - loss: 2.3700
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 43ms/step - accuracy: 0.1783 - loss: 2.3699
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 43ms/step - accuracy: 0.1783 - loss: 2.3698
Trial status: 20 RUNNING
Current time: 2025-10-31 15:06:40. Total running time: 2min 0s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m467/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 57ms/step - accuracy: 0.1143 - loss: 2.9491
[1m468/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 57ms/step - accuracy: 0.1143 - loss: 2.9489[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m530/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 58ms/step - accuracy: 0.1912 - loss: 2.4952[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 34ms/step - accuracy: 0.1963 - loss: 2.4240
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 34ms/step - accuracy: 0.1963 - loss: 2.4240[32m [repeated 225x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.1785 - loss: 2.3686
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.1785 - loss: 2.3686[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 35ms/step - accuracy: 0.1531 - loss: 2.5901[32m [repeated 231x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1786 - loss: 2.3681[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m262/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.1448 - loss: 2.8202
[1m264/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.1448 - loss: 2.8202
[1m265/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.1448 - loss: 2.8202
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.1096 - loss: 2.8936
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.1096 - loss: 2.8935
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.1096 - loss: 2.8935
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.1448 - loss: 2.8203
[1m271/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.1447 - loss: 2.8203[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 69/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 41ms/step - accuracy: 0.1174 - loss: 2.9873[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 5/24
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m471/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.1145 - loss: 2.8524
[1m473/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.1145 - loss: 2.8524
[1m475/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.1145 - loss: 2.8523
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 114ms/step - accuracy: 0.0312 - loss: 3.1274
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1108 - loss: 2.8874 
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1109 - loss: 2.8873
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m331/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1441 - loss: 2.8209
[1m333/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1441 - loss: 2.8209[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m561/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 57ms/step - accuracy: 0.1162 - loss: 2.9374[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.1953 - loss: 2.4232
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.1953 - loss: 2.4232
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.1953 - loss: 2.4232
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 26ms/step - accuracy: 0.1248 - loss: 2.6734
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 26ms/step - accuracy: 0.1247 - loss: 2.6733[32m [repeated 230x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1111 - loss: 2.8855
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1111 - loss: 2.8854[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.1530 - loss: 2.5850[32m [repeated 183x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1112 - loss: 2.8850[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m339/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.1012 - loss: 3.0830
[1m340/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.1013 - loss: 3.0830[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m207/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 38ms/step - accuracy: 0.1187 - loss: 2.9770[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 65ms/step - accuracy: 0.1914 - loss: 2.4927 - val_accuracy: 0.2364 - val_loss: 2.2307
[36m(train_cnn_ray_tune pid=1593444)[0m Epoch 4/23
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 108ms/step - accuracy: 0.1875 - loss: 2.2058
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m56s[0m 48ms/step - accuracy: 0.1787 - loss: 2.3674 - val_accuracy: 0.2302 - val_loss: 2.0287
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:02[0m 105ms/step - accuracy: 0.2500 - loss: 2.3123
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 53ms/step - accuracy: 0.2344 - loss: 2.2646 
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 45ms/step - accuracy: 0.2161 - loss: 2.2693 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 43ms/step - accuracy: 0.2122 - loss: 2.2833
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m488/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 36ms/step - accuracy: 0.1441 - loss: 2.8183
[1m490/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 36ms/step - accuracy: 0.1441 - loss: 2.8182[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.1295 - loss: 2.7231 
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.1295 - loss: 2.7231
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m406/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 38ms/step - accuracy: 0.2558 - loss: 2.0784[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.1949 - loss: 2.4227
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.1949 - loss: 2.4227
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.1949 - loss: 2.4227[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.1948 - loss: 2.4223
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.1948 - loss: 2.4223[32m [repeated 204x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 32ms/step - accuracy: 0.1118 - loss: 2.8802
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 32ms/step - accuracy: 0.1118 - loss: 2.8802[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.1530 - loss: 2.5806[32m [repeated 227x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m323/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1201 - loss: 2.9760 
[1m325/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1201 - loss: 2.9760
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1242 - loss: 2.6976[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 78/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 57ms/step - accuracy: 0.1971 - loss: 2.3817
[1m 79/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 57ms/step - accuracy: 0.1971 - loss: 2.3818[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 84/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 31ms/step - accuracy: 0.1342 - loss: 2.7691[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m78s[0m 64ms/step - accuracy: 0.1166 - loss: 2.9344 - val_accuracy: 0.1591 - val_loss: 2.3577[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m Epoch 3/21[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 96ms/step - accuracy: 0.0938 - loss: 3.0877
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13:12[0m 1s/step - accuracy: 0.2500 - loss: 2.6709
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 33ms/step - accuracy: 0.1979 - loss: 2.6646[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 25ms/step - accuracy: 0.1246 - loss: 2.6957
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 25ms/step - accuracy: 0.1246 - loss: 2.6957
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.1246 - loss: 2.6956
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m492/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 48ms/step - accuracy: 0.1021 - loss: 3.0764
[1m493/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 48ms/step - accuracy: 0.1021 - loss: 3.0764[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1947 - loss: 2.4222 
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1947 - loss: 2.4222
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m503/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 48ms/step - accuracy: 0.1022 - loss: 3.0759[32m [repeated 149x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.1094 - loss: 3.0577
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.1094 - loss: 3.0576
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.1094 - loss: 3.0576[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.1530 - loss: 2.5772
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.1530 - loss: 2.5771[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.1252 - loss: 2.6925
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.1252 - loss: 2.6924
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.1252 - loss: 2.6924
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 34ms/step - accuracy: 0.1946 - loss: 2.4210
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 34ms/step - accuracy: 0.1946 - loss: 2.4210[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.1096 - loss: 3.0552[32m [repeated 128x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 117ms/step - accuracy: 0.1875 - loss: 2.6972
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 34ms/step - accuracy: 0.1946 - loss: 2.4209[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.2109 - loss: 2.6540  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 40ms/step - accuracy: 0.1888 - loss: 2.6922
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m254/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1297 - loss: 2.7763 
[1m257/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1296 - loss: 2.7763
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 18/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.1633 - loss: 2.7618
[1m 20/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.1635 - loss: 2.7622[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m123/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m25s[0m 55ms/step - accuracy: 0.1405 - loss: 2.7492[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 42ms/step - accuracy: 0.1442 - loss: 2.8161 - val_accuracy: 0.1767 - val_loss: 2.3892
[36m(train_cnn_ray_tune pid=1593440)[0m Epoch 6/16
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m182/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 56ms/step - accuracy: 0.1994 - loss: 2.3856
[1m183/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 56ms/step - accuracy: 0.1994 - loss: 2.3855
[1m184/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 56ms/step - accuracy: 0.1994 - loss: 2.3855
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 36ms/step - accuracy: 0.1121 - loss: 2.8781 - val_accuracy: 0.1458 - val_loss: 2.4711
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 4/27
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 52ms/step - accuracy: 0.2350 - loss: 2.1322 - val_accuracy: 0.2588 - val_loss: 1.9530
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 38ms/step - accuracy: 0.0521 - loss: 3.0847  
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.0731 - loss: 2.9553
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m519/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.1206 - loss: 2.9759
[1m520/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.1206 - loss: 2.9759[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m534/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.1207 - loss: 2.9759[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m10s[0m 54ms/step - accuracy: 0.1102 - loss: 3.0504
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m10s[0m 54ms/step - accuracy: 0.1102 - loss: 3.0503[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 35ms/step - accuracy: 0.1532 - loss: 2.5735
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 35ms/step - accuracy: 0.1532 - loss: 2.5734[32m [repeated 157x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m38s[0m 44ms/step - accuracy: 0.2056 - loss: 2.2443[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 92ms/step - accuracy: 0.4062 - loss: 1.8491[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 34ms/step - accuracy: 0.1946 - loss: 2.4190[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 48ms/step - accuracy: 0.2604 - loss: 2.2189  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 51ms/step - accuracy: 0.2617 - loss: 2.1984
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m154/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.1531 - loss: 2.7642
[1m156/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.1531 - loss: 2.7641[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 63/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 50ms/step - accuracy: 0.2505 - loss: 2.1223[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:02:36[0m 37s/step - accuracy: 0.2500 - loss: 2.3430
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 57ms/step - accuracy: 0.2500 - loss: 2.2820   
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 47ms/step - accuracy: 0.2227 - loss: 2.3669 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 45ms/step - accuracy: 0.2189 - loss: 2.3694
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m204/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m20s[0m 55ms/step - accuracy: 0.1823 - loss: 2.6422
[1m205/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 55ms/step - accuracy: 0.1823 - loss: 2.6422
[1m206/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 55ms/step - accuracy: 0.1822 - loss: 2.6423
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 32ms/step - accuracy: 0.1346 - loss: 2.7489
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 32ms/step - accuracy: 0.1346 - loss: 2.7488
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 32ms/step - accuracy: 0.1347 - loss: 2.7488
[36m(train_cnn_ray_tune pid=1593439)[0m Epoch 5/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m201/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 36ms/step - accuracy: 0.1540 - loss: 2.7605
[1m202/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 36ms/step - accuracy: 0.1540 - loss: 2.7605
[1m203/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 36ms/step - accuracy: 0.1540 - loss: 2.7604
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 54ms/step - accuracy: 0.1025 - loss: 3.0723 - val_accuracy: 0.1234 - val_loss: 2.7243[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 28ms/step - accuracy: 0.1313 - loss: 2.7180 - val_accuracy: 0.1667 - val_loss: 2.4579
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.1354 - loss: 2.7680 
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m511/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 30ms/step - accuracy: 0.1282 - loss: 2.7761
[1m513/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 30ms/step - accuracy: 0.1282 - loss: 2.7761[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m525/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 30ms/step - accuracy: 0.1281 - loss: 2.7761[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 47ms/step - accuracy: 0.1059 - loss: 2.9932  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 43ms/step - accuracy: 0.1192 - loss: 2.9401
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 222/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m30s[0m 33ms/step - accuracy: 0.1352 - loss: 2.7514
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m30s[0m 33ms/step - accuracy: 0.1352 - loss: 2.7515[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m556/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 30ms/step - accuracy: 0.1280 - loss: 2.7760
[1m558/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 30ms/step - accuracy: 0.1280 - loss: 2.7760
[1m560/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 30ms/step - accuracy: 0.1280 - loss: 2.7760
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1533 - loss: 2.5704
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1533 - loss: 2.5704[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 38ms/step - accuracy: 0.1726 - loss: 2.3394[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:53[0m 97ms/step - accuracy: 0.1250 - loss: 2.7115[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 54ms/step - accuracy: 0.1107 - loss: 3.0456[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 79/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 50ms/step - a
[36m(train_cnn_ray_tune pid=1593439)[0m ccuracy: 0.1043 - loss: 2.9842
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m171/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 48ms/step - accuracy: 0.2585 - loss: 2.0771
[1m172/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 48ms/step - accuracy: 0.2586 - loss: 2.0769[32m [repeated 162x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 82/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 50ms/step - accuracy: 0.1043 - loss: 2.9837[32m [repeated 186x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43[0m 88ms/step - accuracy: 0.2500 - loss: 2.1263
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.3125 - loss: 2.1401 
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 36ms/step - accuracy: 0.1111 - loss: 2.7359 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.1060 - loss: 2.7162
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1728 - loss: 2.3384 
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1728 - loss: 2.3383
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 54ms/step - accuracy: 0.1109 - loss: 3.0440
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 54ms/step - accuracy: 0.1109 - loss: 3.0439
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 54ms/step - accuracy: 0.1109 - loss: 3.0439
[36m(train_cnn_ray_tune pid=1593435)[0m Epoch 4/17[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 44ms/step - accuracy: 0.1207 - loss: 2.9759 - val_accuracy: 0.1700 - val_loss: 2.5473
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:25[0m 73ms/step - accuracy: 0.1875 - loss: 2.4491
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.1107 - loss: 2.7194 
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 34ms/step - accuracy: 0.1279 - loss: 2.7758 - val_accuracy: 0.1517 - val_loss: 2.5397
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 29ms/step - accuracy: 0.1237 - loss: 2.6596 - val_accuracy: 0.1488 - val_loss: 2.4306[32m [repeated 3x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-10-31 15:07:10. Total running time: 2min 30s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.2778 - loss: 1.9852  
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m350/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.1555 - loss: 2.7521
[1m352/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.1555 - loss: 2.7520[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 37ms/step - accuracy: 0.1905 - loss: 2.4170
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 37ms/step - accuracy: 0.1905 - loss: 2.4170
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 37ms/step - accuracy: 0.1905 - loss: 2.4169
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m364/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.1556 - loss: 2.7515[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1349 - loss: 2.7550
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1349 - loss: 2.7551[32m [repeated 176x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.2015 - loss: 2.3828 
[1m413/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.2016 - loss: 2.3827
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 38ms/step - accuracy: 0.1733 - loss: 2.3354
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 38ms/step - accuracy: 0.1733 - loss: 2.3353[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 37ms/step - accuracy: 0.1963 - loss: 2.3193[32m [repeated 153x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:10[0m 112ms/step - accuracy: 0.2500 - loss: 2.0355
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 38ms/step - accuracy: 0.1734 - loss: 2.3352[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46[0m 92ms/step - accuracy: 0.1250 - loss: 2.4083
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 95/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 31ms/step - accuracy: 0.1356 - loss: 2.7308
[1m 97/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 31ms/step - accuracy: 0.1355 - loss: 2.7312[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m187/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 50ms/step - accuracy: 0.1052 - loss: 2.9796[32m [repeated 224x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1211 - loss: 2.4743 
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m429/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 58ms/step - accuracy: 0.2017 - loss: 2.3824
[1m430/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 58ms/step - accuracy: 0.2018 - loss: 2.3824
[1m431/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 58ms/step - accuracy: 0.2018 - loss: 2.3824
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m391/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 56ms/step - accuracy: 0.1378 - loss: 2.7431
[1m392/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 56ms/step - accuracy: 0.1378 - loss: 2.7431
[1m393/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 56ms/step - accuracy: 0.1378 - loss: 2.7430
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 4/23[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.1562 - loss: 2.9343
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.1413 - loss: 2.8319
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m46s[0m 40ms/step - accuracy: 0.1533 - loss: 2.5699 - val_accuracy: 0.1889 - val_loss: 2.2287[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m462/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 57ms/step - accuracy: 0.1782 - loss: 2.6452
[1m463/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 57ms/step - accuracy: 0.1782 - loss: 2.6452[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 27ms/step - accuracy: 0.1171 - loss: 2.6778
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 27ms/step - accuracy: 0.1171 - loss: 2.6774
[1m 222/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 27ms/step - accuracy: 0.1172 - loss: 2.6768[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m477/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 57ms/step - accuracy: 0.1781 - loss: 2.6451[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m28s[0m 36ms/step - accuracy: 0.1920 - loss: 2.4042
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m28s[0m 36ms/step - accuracy: 0.1920 - loss: 2.4041[32m [repeated 227x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 38ms/step - accuracy: 0.1740 - loss: 2.3316
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 38ms/step - accuracy: 0.1741 - loss: 2.3315[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m28s[0m 36ms/step - accuracy: 0.1921 - loss: 2.4038[32m [repeated 196x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 38ms/step - accuracy: 0.1741 - loss: 2.3315[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m283/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 43ms/step - accuracy: 0.1268 - loss: 2.9271
[1m285/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 42ms/step - accuracy: 0.1267 - loss: 2.9271[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m290/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 49ms/step - accuracy: 0.1073 - loss: 2.9738[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m273/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 49ms/step - accuracy: 0.1070 - loss: 2.9747
[1m274/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 49ms/step - accuracy: 0.1070 - loss: 2.9747
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 49ms/step - accuracy: 0.1070 - loss: 2.9746
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m383/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.2628 - loss: 2.0558 
[1m385/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.2629 - loss: 2.0557
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m550/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 58ms/step - accuracy: 0.2028 - loss: 2.3795
[1m551/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 58ms/step - accuracy: 0.2028 - loss: 2.3794[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 27ms/step - accuracy: 0.1201 - loss: 2.6253
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 27ms/step - accuracy: 0.1201 - loss: 2.6250
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 27ms/step - accuracy: 0.1201 - loss: 2.6248
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m72s[0m 62ms/step - accuracy: 0.1112 - loss: 3.0415 - val_accuracy: 0.1480 - val_loss: 2.4919
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 3/22
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m573/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 56ms/step - accuracy: 0.1776 - loss: 2.6435[32m [repeated 167x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:15[0m 116ms/step - accuracy: 0.1875 - loss: 2.8538
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:23[0m 72ms/step - accuracy: 0.1406 - loss: 2.9176 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:24[0m 73ms/step - accuracy: 0.1424 - loss: 2.8873
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:25[0m 73ms/step - accuracy: 0.1576 - loss: 2.8657
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 71ms/step - accuracy: 0.1610 - loss: 2.8668
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 70ms/step - accuracy: 0.1637 - loss: 2.8658
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 67ms/step - accuracy: 0.1620 - loss: 2.8659
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1613 - loss: 2.8714
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 65ms/step - accuracy: 0.1611 - loss: 2.8753
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 65ms/step - accuracy: 0.1606 - loss: 2.8795
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m538/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 57ms/step - accuracy: 0.1385 - loss: 2.7373
[1m539/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 57ms/step - accuracy: 0.1386 - loss: 2.7373
[1m540/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 57ms/step - accuracy: 0.1386 - loss: 2.7372
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1600 - loss: 2.8852
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 42ms/step - accuracy: 0.1551 - loss: 2.7485 - val_accuracy: 0.1795 - val_loss: 2.3711
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 67ms/step - accuracy: 0.1592 - loss: 2.8909
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1592 - loss: 2.8931
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 125ms/step - accuracy: 0.0938 - loss: 2.8435
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 36ms/step - accuracy: 0.1927 - loss: 2.3984
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 36ms/step - accuracy: 0.1928 - loss: 2.3982[32m [repeated 254x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.1575 - loss: 2.8974
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1559 - loss: 2.8998
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 38ms/step - accuracy: 0.0990 - loss: 2.8605  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.1172 - loss: 2.7986
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1548 - loss: 2.9001
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.1742 - loss: 2.3306
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.1742 - loss: 2.3306[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1533 - loss: 2.9027
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1525 - loss: 2.9045
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m22s[0m 36ms/step - accuracy: 0.1928 - loss: 2.3977[32m [repeated 187x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 38ms/step - accuracy: 0.1742 - loss: 2.3305[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1515 - loss: 2.9065
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1497 - loss: 2.9103
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1489 - loss: 2.9119
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1480 - loss: 2.9136
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1472 - loss: 2.9147
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1457 - loss: 2.9165
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.1375 - loss: 2.6640
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.1375 - loss: 2.6639
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.1375 - loss: 2.6639
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1449 - loss: 2.9173
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1443 - loss: 2.9182
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1437 - loss: 2.9187
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 28/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 35ms/step - accuracy: 0.1453 - loss: 2.7441
[1m 30/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 35ms/step - accuracy: 0.1460 - loss: 2.7404[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 19/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.1412 - loss: 2.7600[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1424 - loss: 2.9197
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1418 - loss: 2.9199
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1409 - loss: 2.9204
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1406 - loss: 2.9203
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1400 - loss: 2.9198
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1398 - loss: 2.9195
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1394 - loss: 2.9192
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1391 - loss: 2.9189
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.1667 - loss: 2.3259  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 36ms/step - accuracy: 0.1663 - loss: 2.3524
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1389 - loss: 2.9186
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1386 - loss: 2.9183
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.1381 - loss: 2.9181
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.1378 - loss: 2.9181
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.1375 - loss: 2.9178
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.1373 - loss: 2.9174
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.1372 - loss: 2.9168
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.1370 - loss: 2.9161
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.1368 - loss: 2.9155
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.1366 - loss: 2.9150
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.1365 - loss: 2.9146
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.1363 - loss: 2.9142
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  59/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1359 - loss: 2.9134
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.1358 - loss: 2.9131
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1356 - loss: 2.9125
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.1354 - loss: 2.9116
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.1353 - loss: 2.9113
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.1353 - loss: 2.9110
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.1351 - loss: 2.9105
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 54ms/step - accuracy: 0.1351 - loss: 2.9097 
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m444/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 49ms/step - accuracy: 0.1094 - loss: 2.9687
[1m445/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 49ms/step - accuracy: 0.1094 - loss: 2.9687[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m49s[0m 42ms/step - accuracy: 0.1742 - loss: 2.3305 - val_accuracy: 0.1981 - val_loss: 2.1429
[36m(train_cnn_ray_tune pid=1593428)[0m Epoch 5/20[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m459/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 49ms/step - accuracy: 0.1096 - loss: 2.9683[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 25ms/step - accuracy: 0.1206 - loss: 2.6383
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 25ms/step - accuracy: 0.1206 - loss: 2.6382
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 25ms/step - accuracy: 0.1206 - loss: 2.6382
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1339 - loss: 2.7605 
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1339 - loss: 2.7605
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.2500 - loss: 2.1407
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.2500 - loss: 2.0678
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 66ms/step - accuracy: 0.2030 - loss: 2.3785 - val_accuracy: 0.2316 - val_loss: 2.1969[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 90ms/step - accuracy: 0.1562 - loss: 2.2463[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.1938 - loss: 2.3912
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.1938 - loss: 2.3912[32m [repeated 249x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 44ms/step - accuracy: 0.1649 - loss: 2.5581  
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 49ms/step - accuracy: 0.1725 - loss: 2.5335
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1338 - loss: 2.7605
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1338 - loss: 2.7605[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.2024 - loss: 2.3061[32m [repeated 192x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1338 - loss: 2.7605[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 35ms/step - accuracy: 0.2015 - loss: 2.3063
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 35ms/step - accuracy: 0.2015 - loss: 2.3063
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 35ms/step - accuracy: 0.2015 - loss: 2.3063
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m172/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.1566 - loss: 2.7098
[1m173/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.1566 - loss: 2.7098[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m170/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.1566 - loss: 2.7098[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 54ms/step - accuracy: 0.1334 - loss: 2.8948
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 54ms/step - accuracy: 0.1334 - loss: 2.8948
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 54ms/step - accuracy: 0.1334 - loss: 2.8947
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 65/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 55ms/step - accuracy: 0.1762 - loss: 2.5765
[1m 66/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 55ms/step - accuracy: 0.1763 - loss: 2.5768
[1m 67/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 55ms/step - accuracy: 0.1764 - loss: 2.5772
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m542/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 49ms/step - accuracy: 0.1106 - loss: 2.9663
[1m543/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 49ms/step - accuracy: 0.1106 - loss: 2.9663[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 9/29[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m555/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 49ms/step - accuracy: 0.1107 - loss: 2.9660[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.1381 - loss: 2.6583
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.1381 - loss: 2.6583
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.1381 - loss: 2.6583
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.2146 - loss: 2.2030 
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.2146 - loss: 2.2029
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 102ms/step - accuracy: 0.0312 - loss: 2.8286
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 31ms/step - accuracy: 0.0816 - loss: 2.7869 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 33ms/step - accuracy: 0.1282 - loss: 2.7396 - val_accuracy: 0.1489 - val_loss: 2.5210[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 37ms/step - accuracy: 0.1648 - loss: 2.4611
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m23s[0m 36ms/step - accuracy: 0.1648 - loss: 2.4611[32m [repeated 149x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 129ms/step - accuracy: 0.2188 - loss: 1.8478
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 44ms/step - accuracy: 0.2150 - loss: 2.2015
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 44ms/step - accuracy: 0.2150 - loss: 2.2015[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m16s[0m 35ms/step - accuracy: 0.2030 - loss: 2.3066[32m [repeated 189x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 44ms/step - accuracy: 0.2150 - loss: 2.2014[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m296/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.1578 - loss: 2.7048
[1m297/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.1578 - loss: 2.7047[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m104/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 61ms/step - accuracy: 0.2056 - loss: 2.3103[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m320/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1579 - loss: 2.7038 
[1m321/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1579 - loss: 2.7038
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m52s[0m 55ms/step - accuracy: 0.1320 - loss: 2.8909
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m52s[0m 55ms/step - accuracy: 0.1320 - loss: 2.8909
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m52s[0m 55ms/step - accuracy: 0.1319 - loss: 2.8908[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m106/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 61ms/step - accuracy: 0.2058 - loss: 2.3102
[1m107/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m28s[0m 61ms/step - accuracy: 0.2058 - loss: 2.3102
[1m108/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m28s[0m 61ms/step - accuracy: 0.2059 - loss: 2.3101
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1955 - loss: 2.3822 
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1955 - loss: 2.3821
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m356/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 38ms/step - accuracy: 0.1582 - loss: 2.7027
[1m357/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 38ms/step - accuracy: 0.1582 - loss: 2.7027[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 32ms/step - accuracy: 0.1336 - loss: 2.7602
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 32ms/step - accuracy: 0.1336 - loss: 2.7602
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 32ms/step - accuracy: 0.1336 - loss: 2.7602
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 7/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m374/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 38ms/step - accuracy: 0.1583 - loss: 2.7022[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 62ms/step - accuracy: 0.2093 - loss: 2.3052
[1m168/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 61ms/step - accuracy: 0.2094 - loss: 2.3051
[1m169/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 61ms/step - accuracy: 0.2094 - loss: 2.3050
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 56ms/step - accuracy: 0.1111 - loss: 2.9652 - val_accuracy: 0.1260 - val_loss: 2.6639[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m31s[0m 39ms/step - accuracy: 0.1910 - loss: 2.2520
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m31s[0m 39ms/step - accuracy: 0.1910 - loss: 2.2519[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 105ms/step - accuracy: 0.0938 - loss: 3.1979[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 45ms/step - accuracy: 0.2160 - loss: 2.1978
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 45ms/step - accuracy: 0.2160 - loss: 2.1977[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m49s[0m 56ms/step - accuracy: 0.1303 - loss: 2.8905[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.1959 - loss: 2.3800[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m186/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 61ms/step - accuracy: 0.2100 - loss: 2.3036
[1m187/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 61ms/step - accuracy: 0.2100 - loss: 2.3036[32m [repeated 144x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m209/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 58ms/step - accuracy: 0.1809 - loss: 2.5832[32m [repeated 219x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 29ms/step - accuracy: 0.1385 - loss: 2.6553 - val_accuracy: 0.1774 - val_loss: 2.4069
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m29s[0m 39ms/step - accuracy: 0.1909 - loss: 2.2506
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m29s[0m 39ms/step - accuracy: 0.1909 - loss: 2.2506
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m29s[0m 39ms/step - accuracy: 0.1909 - loss: 2.2506
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:11[0m 113ms/step - accuracy: 0.1875 - loss: 2.1720
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1875 - loss: 2.3245  
Trial status: 20 RUNNING
Current time: 2025-10-31 15:07:40. Total running time: 3min 0s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m367/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.1363 - loss: 2.7030
[1m369/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1363 - loss: 2.7029[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m Epoch 6/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m359/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.2919 - loss: 1.9449
[1m360/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.2920 - loss: 1.9448
[1m361/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.2920 - loss: 1.9448
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m510/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 38ms/step - accuracy: 0.1596 - loss: 2.6984[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m164/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 50ms/step - accuracy: 0.3157 - loss: 1.9166
[1m165/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 50ms/step - accuracy: 0.3157 - loss: 1.9167
[1m166/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 50ms/step - accuracy: 0.3156 - loss: 1.9168
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1238 - loss: 2.6081
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.1246 - loss: 2.6045[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:21[0m 121ms/step - accuracy: 0.1875 - loss: 3.1195
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 36ms/step - accuracy: 0.1969 - loss: 2.3755
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 36ms/step - accuracy: 0.1969 - loss: 2.3754[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 37ms/step - accuracy: 0.1644 - loss: 2.4603[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 35ms/step - accuracy: 0.2041 - loss: 2.3065[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1736 - loss: 2.8671 
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 48ms/step - accuracy: 0.1742 - loss: 2.7790 
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m266/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 62ms/step - accuracy: 0.2120 - loss: 2.3003
[1m267/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 62ms/step - accuracy: 0.2120 - loss: 2.3003[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m135/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 50ms/step - accuracy: 0.1256 - loss: 2.8756[32m [repeated 161x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m287/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 61ms/step - accuracy: 0.2123 - loss: 2.3002
[1m288/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 61ms/step - accuracy: 0.2123 - loss: 2.3002
[1m289/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 61ms/step - accuracy: 0.2123 - loss: 2.3002
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 37ms/step - accuracy: 0.1336 - loss: 2.7600 - val_accuracy: 0.1602 - val_loss: 2.4254[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:50[0m 95ms/step - accuracy: 0.0625 - loss: 2.9866
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.0729 - loss: 2.8258 
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 35ms/step - accuracy: 0.2044 - loss: 2.3064
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 35ms/step - accuracy: 0.2044 - loss: 2.3064
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 35ms/step - accuracy: 0.2044 - loss: 2.3064
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:17[0m 118ms/step - accuracy: 0.1250 - loss: 2.4159
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.0972 - loss: 2.5011  
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m454/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 41ms/step - accuracy: 0.2940 - loss: 1.9420
[1m455/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 41ms/step - accuracy: 0.2940 - loss: 1.9420[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m Epoch 6/18[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1642 - loss: 2.4600 
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1642 - loss: 2.4600
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m482/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 41ms/step - accuracy: 0.2945 - loss: 1.9412[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m39s[0m 56ms/step - accuracy: 0.1280 - loss: 2.8898
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m39s[0m 56ms/step - accuracy: 0.1279 - loss: 2.8898[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.1602 - loss: 2.6961 - val_accuracy: 0.1791 - val_loss: 2.3495
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 89ms/step - accuracy: 0.2500 - loss: 2.3510
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:26[0m 126ms/step - accuracy: 0.2500 - loss: 2.2474
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.1641 - loss: 2.4598
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.1641 - loss: 2.4597[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m39s[0m 57ms/step - accuracy: 0.1279 - loss: 2.8898[32m [repeated 145x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 36ms/step - accuracy: 0.2711 - loss: 2.0447[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2656 - loss: 2.2192 
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.2786 - loss: 2.1680 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 52ms/step - accuracy: 0.2804 - loss: 2.1670
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.2823 - loss: 2.1625
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2802 - loss: 2.1712
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2774 - loss: 2.1815
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2728 - loss: 2.1911
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2706 - loss: 2.1982
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2677 - loss: 2.2079
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.2611 - loss: 2.2242
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m352/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 61ms/step - accuracy: 0.2133 - loss: 2.3000
[1m353/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 61ms/step - accuracy: 0.2133 - loss: 2.3000[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m338/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 58ms/step - accuracy: 0.1528 - loss: 2.6442[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 51ms/step - accuracy: 0.2593 - loss: 2.2302 
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.2598 - loss: 2.2253 
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m356/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.1316 - loss: 2.9194 
[1m358/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.1316 - loss: 2.9194
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m59s[0m 50ms/step - accuracy: 0.2166 - loss: 2.1954 - val_accuracy: 0.2607 - val_loss: 1.9726[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m422/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.1815 - loss: 2.5796
[1m423/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.1815 - loss: 2.5796[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 10/29[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:48[0m 145ms/step - accuracy: 0.1875 - loss: 1.9456
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 34ms/step - accuracy: 0.1875 - loss: 2.0478  
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 44ms/step - accuracy: 0.1315 - loss: 2.9183[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 47ms/step - accuracy: 0.2478 - loss: 2.1337
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 47ms/step - accuracy: 0.2477 - loss: 2.1336
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 47ms/step - accuracy: 0.2476 - loss: 2.1336
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m406/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 61ms/step - accuracy: 0.2139 - loss: 2.3001
[1m407/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 61ms/step - accuracy: 0.2139 - loss: 2.3001
[1m408/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 61ms/step - accuracy: 0.2140 - loss: 2.3001
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.2147 - loss: 2.2186
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.2145 - loss: 2.2246[32m [repeated 180x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 35ms/step - accuracy: 0.1360 - loss: 2.7009 - val_accuracy: 0.1499 - val_loss: 2.4975
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 88ms/step - accuracy: 0.2188 - loss: 2.6454
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.2718 - loss: 2.0420
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.2718 - loss: 2.0420[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m34s[0m 57ms/step - accuracy: 0.1273 - loss: 2.8891[32m [repeated 154x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 37ms/step - accuracy: 0.1639 - loss: 2.4585[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m327/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 51ms/step - accuracy: 0.1262 - loss: 2.8778
[1m328/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 51ms/step - accuracy: 0.1262 - loss: 2.8778[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m145/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m17s[0m 40ms/step - accuracy: 0.1653 - loss: 2.6258[32m [repeated 135x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 47ms/step - accuracy: 0.2963 - loss: 1.9379 - val_accuracy: 0.2873 - val_loss: 1.8878
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m85s[0m 41ms/step - accuracy: 0.1974 - loss: 2.3728 - val_accuracy: 0.2290 - val_loss: 2.2280
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.2049 - loss: 2.3060 - val_accuracy: 0.2266 - val_loss: 2.1533
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:43[0m 140ms/step - accuracy: 0.1875 - loss: 2.0884
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.1719 - loss: 2.1335 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.1701 - loss: 2.1765
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 55ms/step - accuracy: 0.1821 - loss: 2.1947
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 49ms/step - accuracy: 0.1917 - loss: 2.1962 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 45ms/step - accuracy: 0.1997 - loss: 2.1953
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m475/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 61ms/step - accuracy: 0.2149 - loss: 2.2995
[1m476/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 61ms/step - accuracy: 0.2150 - loss: 2.2995[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m Epoch 5/17[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 115ms/step - accuracy: 0.4375 - loss: 1.6032
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 50ms/step - accuracy: 0.3663 - loss: 1.7604  
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m476/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.3127 - loss: 1.9223[32m [repeated 128x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m32s[0m 57ms/step - accuracy: 0.1271 - loss: 2.8886
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m32s[0m 57ms/step - accuracy: 0.1271 - loss: 2.8886
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m32s[0m 57ms/step - accuracy: 0.1271 - loss: 2.8885[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m390/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.1258 - loss: 2.8790 
[1m391/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.1258 - loss: 2.8791
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 37ms/step - accuracy: 0.2072 - loss: 2.2760
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 37ms/step - accuracy: 0.2073 - loss: 2.2759[32m [repeated 204x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.1638 - loss: 2.4578
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.1638 - loss: 2.4578[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1372 - loss: 2.5617[32m [repeated 203x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.1638 - loss: 2.4579[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 38ms/step - accuracy: 0.3160 - loss: 1.8372  
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.3069 - loss: 1.8726
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m100/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m19s[0m 41ms/step - accuracy: 0.3350 - loss: 1.8484
[1m102/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m19s[0m 41ms/step - accuracy: 0.3350 - loss: 1.8484[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 40ms/step - accuracy: 0.1633 - loss: 2.6382[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m433/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 52ms/step - accuracy: 0.1254 - loss: 2.8799
[1m434/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 52ms/step - accuracy: 0.1254 - loss: 2.8800
[1m435/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 52ms/step - accuracy: 0.1254 - loss: 2.8800
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 41ms/step - accuracy: 0.2718 - loss: 2.0419 - val_accuracy: 0.2820 - val_loss: 1.9026
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:24[0m 124ms/step - accuracy: 0.2500 - loss: 1.8453
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m555/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 61ms/step - accuracy: 0.2161 - loss: 2.2984
[1m556/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 61ms/step - accuracy: 0.2161 - loss: 2.2984[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.1638 - loss: 2.4577 - val_accuracy: 0.1861 - val_loss: 2.1928
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:22[0m 122ms/step - accuracy: 0.0625 - loss: 2.5497
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 5/23[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m575/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 51ms/step - accuracy: 0.3129 - loss: 1.9221[32m [repeated 171x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.1375 - loss: 2.5607
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.1375 - loss: 2.5606
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 26ms/step - accuracy: 0.1375 - loss: 2.5606[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 49ms/step - accuracy: 0.1310 - loss: 2.9159 - val_accuracy: 0.1737 - val_loss: 2.5014
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1381 - loss: 2.5583 
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1381 - loss: 2.5583
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 36ms/step - accuracy: 0.2179 - loss: 2.2257
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 36ms/step - accuracy: 0.2180 - loss: 2.2256[32m [repeated 193x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1382 - loss: 2.5577
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1382 - loss: 2.5577[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m32s[0m 37ms/step - accuracy: 0.2066 - loss: 2.2775[32m [repeated 259x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 39ms/step - accuracy: 0.1898 - loss: 2.2455[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.1042 - loss: 2.5177  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.0962 - loss: 2.5044
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 36/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.1269 - loss: 2.9158
[1m 38/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 39ms/step - accuracy: 0.1267 - loss: 2.9162[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 34/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.1272 - loss: 2.9153[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m338/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.1624 - loss: 2.6425
[1m340/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.1623 - loss: 2.6426
[1m342/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1623 - loss: 2.6427
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 163ms/step - accuracy: 0.2500 - loss: 2.0199
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 50ms/step - accuracy: 0.2734 - loss: 2.0067  
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m472/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.1614 - loss: 2.6468
[1m474/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.1614 - loss: 2.6468[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 141ms/step - accuracy: 0.2500 - loss: 2.4922[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m Epoch 7/25[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m495/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 39ms/step - accuracy: 0.1614 - loss: 2.6473[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 68ms/step - accuracy: 0.2165 - loss: 2.2979 - val_accuracy: 0.2414 - val_loss: 2.1816[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1279 - loss: 2.5396 
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1280 - loss: 2.5396
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m26s[0m 37ms/step - accuracy: 0.2073 - loss: 2.2770
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m26s[0m 37ms/step - accuracy: 0.2074 - loss: 2.2770[32m [repeated 204x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m527/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 38ms/step - accuracy: 0.1614 - loss: 2.6479
[1m529/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 38ms/step - accuracy: 0.1614 - loss: 2.6480
[1m531/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 38ms/step - accuracy: 0.1614 - loss: 2.6480
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 26ms/step - accuracy: 0.1387 - loss: 2.5548
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 26ms/step - accuracy: 0.1387 - loss: 2.5548[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m19s[0m 56ms/step - accuracy: 0.1267 - loss: 2.8847[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 26ms/step - accuracy: 0.1509 - loss: 2.5914[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 24/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 63ms/step - accuracy: 0.1725 - loss: 2.5971
[1m 25/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 62ms/step - accuracy: 0.1721 - loss: 2.5969[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 30/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 64ms/step - accuracy: 0.2355 - loss: 2.2239[32m [repeated 99x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-10-31 15:08:10. Total running time: 3min 30s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:25[0m 146ms/step - accuracy: 0.1562 - loss: 2.7328
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 64ms/step - accuracy: 0.1562 - loss: 2.6640  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m425/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3362 - loss: 1.8529
[1m427/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3362 - loss: 1.8529[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 103ms/step - accuracy: 0.1875 - loss: 2.8256[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 11/29[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1387 - loss: 2.7091
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1387 - loss: 2.7091
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1387 - loss: 2.7090
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m449/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3363 - loss: 1.8528[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 34ms/step - accuracy: 0.1401 - loss: 2.6797 - val_accuracy: 0.1539 - val_loss: 2.4742[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.1387 - loss: 2.7087
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.1387 - loss: 2.7087
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.1387 - loss: 2.7087
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m29s[0m 35ms/step - accuracy: 0.1545 - loss: 2.4414
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m29s[0m 35ms/step - accuracy: 0.1546 - loss: 2.4412[32m [repeated 145x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 57ms/step - accuracy: 0.1268 - loss: 2.8829
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 57ms/step - accuracy: 0.1268 - loss: 2.8829
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 57ms/step - accuracy: 0.1268 - loss: 2.8829
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.1388 - loss: 2.7084
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.1388 - loss: 2.7084[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2091 - loss: 2.2734[32m [repeated 180x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 26ms/step - accuracy: 0.1294 - loss: 2.5363[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m153/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 59ms/step - accuracy: 0.1984 - loss: 2.4859
[1m154/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 59ms/step - accuracy: 0.1984 - loss: 2.4860[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m280/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 41ms/step - accuracy: 0.1275 - loss: 2.8897[32m [repeated 194x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.2240 - loss: 2.5021  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2097 - loss: 2.5491
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.1509 - loss: 2.5911 - val_accuracy: 0.1858 - val_loss: 2.3562
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1771 - loss: 2.5144 
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:01[0m 105ms/step - accuracy: 0.2500 - loss: 2.3837
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.1597 - loss: 2.5758  
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m552/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3365 - loss: 1.8520
[1m554/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3366 - loss: 1.8519[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.1270 - loss: 2.8815
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.1270 - loss: 2.8815
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.1270 - loss: 2.8814
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46[0m 92ms/step - accuracy: 0.2500 - loss: 2.4946[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.1270 - loss: 2.8814
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.1270 - loss: 2.8813
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.1270 - loss: 2.8813
[36m(train_cnn_ray_tune pid=1593429)[0m Epoch 7/15[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m354/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.1279 - loss: 2.8866[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 44ms/step - accuracy: 0.1614 - loss: 2.6489 - val_accuracy: 0.1802 - val_loss: 2.3333
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m173/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 61ms/step - accuracy: 0.2439 - loss: 2.2178
[1m174/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 61ms/step - accuracy: 0.2439 - loss: 2.2179
[1m175/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 61ms/step - accuracy: 0.2439 - loss: 2.2179
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 35ms/step - accuracy: 0.2190 - loss: 2.2286
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 35ms/step - accuracy: 0.2190 - loss: 2.2286[32m [repeated 149x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1271 - loss: 2.8809 
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1271 - loss: 2.8809
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1271 - loss: 2.8808
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1271 - loss: 2.8807[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m24s[0m 35ms/step - accuracy: 0.1586 - loss: 2.4318[32m [repeated 204x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1271 - loss: 2.8807[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m263/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1481 - loss: 2.6590 
[1m266/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1480 - loss: 2.6590
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m134/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.1780 - loss: 2.6156
[1m136/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.1778 - loss: 2.6158[32m [repeated 166x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m194/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 61ms/step - accuracy: 0.2437 - loss: 2.2189[32m [repeated 194x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 52ms/step - accuracy: 0.2500 - loss: 2.2840 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.2500 - loss: 2.2202 
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m55s[0m 47ms/step - accuracy: 0.1894 - loss: 2.2450 - val_accuracy: 0.2115 - val_loss: 2.0983[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 45ms/step - accuracy: 0.3367 - loss: 1.8517 - val_accuracy: 0.3362 - val_loss: 1.8382
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.0312 - loss: 2.7209     
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 39ms/step - accuracy: 0.1924 - loss: 2.2198
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 39ms/step - accuracy: 0.1921 - loss: 2.2190
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 39ms/step - accuracy: 0.1919 - loss: 2.2182
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m453/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.1289 - loss: 2.8827
[1m455/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.1289 - loss: 2.8826[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 118ms/step - accuracy: 0.3438 - loss: 1.8407[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m Epoch 9/29[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m466/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 42ms/step - accuracy: 0.1290 - loss: 2.8823[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m257/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 60ms/step - accuracy: 0.2426 - loss: 2.2222
[1m258/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 60ms/step - accuracy: 0.2425 - loss: 2.2222
[1m259/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 60ms/step - accuracy: 0.2425 - loss: 2.2223[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m21s[0m 36ms/step - accuracy: 0.1607 - loss: 2.4272
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m21s[0m 36ms/step - accuracy: 0.1608 - loss: 2.4271[32m [repeated 195x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 57ms/step - accuracy: 0.1273 - loss: 2.8786
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 57ms/step - accuracy: 0.1273 - loss: 2.8786[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2193 - loss: 2.2290[32m [repeated 189x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 57ms/step - accuracy: 0.1273 - loss: 2.8788[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m282/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 60ms/step - accuracy: 0.2422 - loss: 2.2230
[1m283/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 60ms/step - accuracy: 0.2422 - loss: 2.2230[32m [repeated 144x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m263/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 38ms/step - accuracy: 0.1730 - loss: 2.6201[32m [repeated 167x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.1299 - loss: 2.5346 - val_accuracy: 0.1560 - val_loss: 2.3459
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 36ms/step - accuracy: 0.1390 - loss: 2.7050 - val_accuracy: 0.1661 - val_loss: 2.3964
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:16[0m 117ms/step - accuracy: 0.0000e+00 - loss: 2.8778
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.0156 - loss: 2.9111      
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 57ms/step - accuracy: 0.1274 - loss: 2.8775
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 57ms/step - accuracy: 0.1274 - loss: 2.8775
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 57ms/step - accuracy: 0.1274 - loss: 2.8775
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m581/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.1300 - loss: 2.8786
[1m582/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.1300 - loss: 2.8786[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m327/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1726 - loss: 2.6199 
[1m329/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1726 - loss: 2.6199
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 6/27
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m416/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.3462 - loss: 1.8360[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.1224 - loss: 2.7143
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 33ms/step - accuracy: 0.1228 - loss: 2.7134
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 33ms/step - accuracy: 0.1236 - loss: 2.7116
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 29ms/step - accuracy: 0.1380 - loss: 2.4925
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 29ms/step - accuracy: 0.1380 - loss: 2.4926[32m [repeated 219x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 37ms/step - accuracy: 0.2118 - loss: 2.2644
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 37ms/step - accuracy: 0.2118 - loss: 2.2644[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 27ms/step - accuracy: 0.1466 - loss: 2.5775[32m [repeated 195x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 37ms/step - accuracy: 0.2119 - loss: 2.2642[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m400/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 60ms/step - accuracy: 0.1941 - loss: 2.4975
[1m401/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 60ms/step - accuracy: 0.1941 - loss: 2.4975[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m366/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 59ms/step - accuracy: 0.1656 - loss: 2.5744[32m [repeated 163x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 47ms/step - accuracy: 0.1301 - loss: 2.8785 - val_accuracy: 0.1730 - val_loss: 2.4865
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 9/24
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 100ms/step - accuracy: 0.0938 - loss: 2.9136
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.3058 - loss: 1.9482 
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.3058 - loss: 1.9482
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m458/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.1722 - loss: 2.6180
[1m460/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.1722 - loss: 2.6180[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m390/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.1241 - loss: 2.8430 
[1m391/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.1241 - loss: 2.8430
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m460/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 59ms/step - accuracy: 0.1938 - loss: 2.4986[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m432/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 59ms/step - accuracy: 0.2406 - loss: 2.2262
[1m433/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 59ms/step - accuracy: 0.2406 - loss: 2.2262
[1m434/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 59ms/step - accuracy: 0.2406 - loss: 2.2262
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.1634 - loss: 2.4206
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.1634 - loss: 2.4205[32m [repeated 200x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 37ms/step - accuracy: 0.2127 - loss: 2.2615
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 37ms/step - accuracy: 0.2127 - loss: 2.2615[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.1636 - loss: 2.4202[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 36ms/step - accuracy: 0.2203 - loss: 2.2282[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m321/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 41ms/step - accuracy: 0.3576 - loss: 1.7857
[1m323/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 41ms/step - accuracy: 0.3576 - loss: 1.7857[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m110/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.1401 - loss: 2.6302[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 35ms/step - accuracy: 0.1450 - loss: 2.6551 - val_accuracy: 0.1621 - val_loss: 2.4527
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 12/29
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 121ms/step - accuracy: 0.1562 - loss: 2.5265
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1636 - loss: 2.4201 
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1636 - loss: 2.4200
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m75s[0m 64ms/step - accuracy: 0.1275 - loss: 2.8766 - val_accuracy: 0.1615 - val_loss: 2.4186
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 4/22
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:10[0m 112ms/step - accuracy: 0.2500 - loss: 2.3165
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m519/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 51ms/step - accuracy: 0.1253 - loss: 2.8397
[1m520/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 51ms/step - accuracy: 0.1253 - loss: 2.8397[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.2344 - loss: 2.3951  
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.2257 - loss: 2.4915
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2104 - loss: 2.6211
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.2066 - loss: 2.6534
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.1967 - loss: 2.7066 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1785 - loss: 2.7833
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m511/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 59ms/step - accuracy: 0.2402 - loss: 2.2268[32m [repeated 160x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1766 - loss: 2.7919
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1748 - loss: 2.7988
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1729 - loss: 2.8034
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1716 - loss: 2.8064
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1704 - loss: 2.8082
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1694 - loss: 2.8099
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m26s[0m 33ms/step - accuracy: 0.1421 - loss: 2.6622
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m26s[0m 33ms/step - accuracy: 0.1421 - loss: 2.6621
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m26s[0m 33ms/step - accuracy: 0.1421 - loss: 2.6620
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1669 - loss: 2.8139
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1659 - loss: 2.8148
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1651 - loss: 2.8152
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 27ms/step - accuracy: 0.1375 - loss: 2.4955
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 27ms/step - accuracy: 0.1375 - loss: 2.4954[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1635 - loss: 2.8160
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1629 - loss: 2.8155
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1621 - loss: 2.8146
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1616 - loss: 2.8130
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1613 - loss: 2.8126
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 36ms/step - accuracy: 0.1647 - loss: 2.4168
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 36ms/step - accuracy: 0.1647 - loss: 2.4168[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 27ms/step - accuracy: 0.1375 - loss: 2.4953[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 46ms/step - accuracy: 0.2490 - loss: 2.0855[32m [repeated 131x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1606 - loss: 2.8117
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1601 - loss: 2.8116
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1596 - loss: 2.8118
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1591 - loss: 2.8118
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1587 - loss: 2.8118
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1579 - loss: 2.8127
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1572 - loss: 2.8134
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 56ms/step - accuracy: 0.3465 - loss: 1.8340 - val_accuracy: 0.3645 - val_loss: 1.7773
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1569 - loss: 2.8135
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1567 - loss: 2.8136
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m221/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 40ms/step - accuracy: 0.1413 - loss: 2.8317
[1m222/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 40ms/step - accuracy: 0.1413 - loss: 2.8317[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m228/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 40ms/step - accuracy: 0.1414 - loss: 2.8322[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1565 - loss: 2.8136
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 124ms/step - accuracy: 0.2812 - loss: 2.4577
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 57ms/step - accuracy: 0.2656 - loss: 2.3801  
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1563 - loss: 2.8136
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1562 - loss: 2.8135
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1561 - loss: 2.8135
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1560 - loss: 2.8137
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1558 - loss: 2.8141
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1556 - loss: 2.8143
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1554 - loss: 2.8144
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1552 - loss: 2.8146
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1549 - loss: 2.8148
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1548 - loss: 2.8150
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1546 - loss: 2.8152
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.1543 - loss: 2.8156
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1542 - loss: 2.8157
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.1539 - loss: 2.8157
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.1536 - loss: 2.8160
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.1534 - loss: 2.8162
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.1532 - loss: 2.8163
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.2118 - loss: 2.2045  
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.1530 - loss: 2.8161
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.1529 - loss: 2.8156
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.1528 - loss: 2.8149
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1527 - loss: 2.8143
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1526 - loss: 2.8136
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1524 - loss: 2.8131
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1524 - loss: 2.8129
Trial status: 20 RUNNING
Current time: 2025-10-31 15:08:40. Total running time: 4min 0s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1523 - loss: 2.8126
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1522 - loss: 2.8125
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1522 - loss: 2.8123
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1520 - loss: 2.8120
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1519 - loss: 2.8117
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1518 - loss: 2.8115
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1517 - loss: 2.8113
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1517 - loss: 2.8111
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  88/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 56ms/step - accuracy: 0.1515 - loss: 2.8106 
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.2129 - loss: 2.2606 - val_accuracy: 0.2387 - val_loss: 2.1540
[36m(train_cnn_ray_tune pid=1593441)[0m Epoch 5/22[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:57[0m 100ms/step - accuracy: 0.2500 - loss: 1.9880[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m360/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.1449 - loss: 2.6257
[1m363/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.1449 - loss: 2.6256[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.2205 - loss: 2.2278 - val_accuracy: 0.2303 - val_loss: 2.1400
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m377/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 30ms/step - accuracy: 0.1451 - loss: 2.6253[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.2153 - loss: 2.1690 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 30ms/step - accuracy: 0.1904 - loss: 2.2150
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.1382 - loss: 2.4928
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.1382 - loss: 2.4927
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.1382 - loss: 2.4927
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m  88/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 31ms/step - accuracy: 0.2573 - loss: 2.1262
[1m  90/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 31ms/step - accuracy: 0.2573 - loss: 2.1264[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m331/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1418 - loss: 2.8357 
[1m333/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1418 - loss: 2.8358
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 25ms/step - accuracy: 0.1400 - loss: 2.4995
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 25ms/step - accuracy: 0.1400 - loss: 2.4995[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 53ms/step - accuracy: 0.1474 - loss: 2.8066[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.1382 - loss: 2.4925[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 66ms/step - accuracy: 0.1933 - loss: 2.5006 - val_accuracy: 0.2074 - val_loss: 2.2498[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m141/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.1686 - loss: 2.5773
[1m143/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.1686 - loss: 2.5773[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m114/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m20s[0m 45ms/step - accuracy: 0.3721 - loss: 1.7742[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 105ms/step - accuracy: 0.0938 - loss: 3.0620
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.0955 - loss: 2.9113  
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.2188 - loss: 2.5588
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.1875 - loss: 2.5657
[36m(train_cnn_ray_tune pid=1593422)[0m Epoch 10/29[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 82ms/step - accuracy: 0.2500 - loss: 1.8410[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m543/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 29ms/step - accuracy: 0.1467 - loss: 2.6225
[1m545/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 29ms/step - accuracy: 0.1467 - loss: 2.6225[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m30s[0m 32ms/step - accuracy: 0.2556 - loss: 2.1302
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.3069 - loss: 1.9424 - val_accuracy: 0.3269 - val_loss: 1.7972
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m444/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.1418 - loss: 2.8357[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.5035 - loss: 1.6379 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.4715 - loss: 1.7107
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m60s[0m 51ms/step - accuracy: 0.2497 - loss: 2.0837 - val_accuracy: 0.3563 - val_loss: 1.8457
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 33ms/step - accuracy: 0.2550 - loss: 2.1315
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 33ms/step - accuracy: 0.2549 - loss: 2.1317[32m [repeated 135x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 48ms/step - accuracy: 0.2435 - loss: 2.4131 
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 26ms/step - accuracy: 0.1385 - loss: 2.4904
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 26ms/step - accuracy: 0.1385 - loss: 2.4904[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 42ms/step - accuracy: 0.2673 - loss: 1.8913[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 26ms/step - accuracy: 0.1385 - loss: 2.4905[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 44ms/step - accuracy: 0.3600 - loss: 1.7832 - val_accuracy: 0.3739 - val_loss: 1.8065[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m273/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.1654 - loss: 2.5818
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.1654 - loss: 2.5817[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 62/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 42ms/step - accuracy: 0.3921 - loss: 1.6886[32m [repeated 161x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:07[0m 161ms/step - accuracy: 0.0625 - loss: 2.7871
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.0972 - loss: 2.6064  [32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m116/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m26s[0m 56ms/step - accuracy: 0.1819 - loss: 2.4813
[1m117/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 56ms/step - accuracy: 0.1819 - loss: 2.4814
[1m118/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 56ms/step - accuracy: 0.1819 - loss: 2.4814
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 13/29[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 112ms/step - accuracy: 0.0312 - loss: 2.8112
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m335/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1655 - loss: 2.5813
[1m337/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1655 - loss: 2.5813[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m354/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 38ms/step - accuracy: 0.1655 - loss: 2.5812[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 29ms/step - accuracy: 0.1402 - loss: 2.4989 - val_accuracy: 0.1858 - val_loss: 2.2762[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m27s[0m 34ms/step - accuracy: 0.2526 - loss: 2.1365
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m27s[0m 34ms/step - accuracy: 0.2526 - loss: 2.1366[32m [repeated 224x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.1386 - loss: 2.4893
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.1386 - loss: 2.4893[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.1994 - loss: 2.1901[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.1386 - loss: 2.4892[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1995 - loss: 2.1899 
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1995 - loss: 2.1899
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 33ms/step - accuracy: 0.1470 - loss: 2.6218 - val_accuracy: 0.1602 - val_loss: 2.4329
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m133/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 62ms/step - accuracy: 0.2598 - loss: 2.1627
[1m134/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 62ms/step - accuracy: 0.2598 - loss: 2.1627[32m [repeated 144x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m176/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 43ms/step - accuracy: 0.3893 - loss: 1.7092[32m [repeated 202x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:53[0m 97ms/step - accuracy: 0.0625 - loss: 2.9143
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.0807 - loss: 2.6813 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.1031 - loss: 2.6099
[36m(train_cnn_ray_tune pid=1593431)[0m Epoch 8/18
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m463/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.1661 - loss: 2.5790
[1m465/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.1661 - loss: 2.5790[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 47ms/step - accuracy: 0.1417 - loss: 2.8354 - val_accuracy: 0.1774 - val_loss: 2.4650
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 10/24
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m249/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 43ms/step - accuracy: 0.3903 - loss: 1.7108
[1m251/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 43ms/step - accuracy: 0.3903 - loss: 1.7108
[1m253/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 42ms/step - accuracy: 0.3903 - loss: 1.7109
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m383/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.3641 - loss: 1.7760[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.1386 - loss: 2.4892 - val_accuracy: 0.1665 - val_loss: 2.3135
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 35ms/step - accuracy: 0.2511 - loss: 2.1396
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 35ms/step - accuracy: 0.2511 - loss: 2.1396[32m [repeated 205x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 33ms/step - accuracy: 0.1428 - loss: 2.6508
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 33ms/step - accuracy: 0.1428 - loss: 2.6508[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m33s[0m 37ms/step - accuracy: 0.1874 - loss: 2.3288[32m [repeated 234x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 39ms/step - accuracy: 0.2004 - loss: 2.1887[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 33ms/step - accuracy: 0.1428 - loss: 2.6507
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 33ms/step - accuracy: 0.1428 - loss: 2.6507
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 33ms/step - accuracy: 0.1429 - loss: 2.6507
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m218/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m22s[0m 61ms/step - accuracy: 0.2589 - loss: 2.1649
[1m220/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m22s[0m 61ms/step - accuracy: 0.2589 - loss: 2.1650[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m249/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 58ms/step - accuracy: 0.1763 - loss: 2.4923[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 145/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 28ms/step - accuracy: 0.1543 - loss: 2.4493
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 28ms/step - accuracy: 0.1543 - loss: 2.4492
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 29ms/step - accuracy: 0.1543 - loss: 2.4492
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 120ms/step - accuracy: 0.1875 - loss: 2.7575
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m354/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.3910 - loss: 1.7124
[1m356/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.3910 - loss: 1.7124[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m474/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 50ms/step - accuracy: 0.3640 - loss: 1.7753[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2499 - loss: 2.1416
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2499 - loss: 2.1417[32m [repeated 215x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 39ms/step - accuracy: 0.2013 - loss: 2.1873
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 39ms/step - accuracy: 0.2013 - loss: 2.1873[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m28s[0m 38ms/step - accuracy: 0.1857 - loss: 2.3325[32m [repeated 223x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.1432 - loss: 2.6490[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m301/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 61ms/step - accuracy: 0.2581 - loss: 2.1657
[1m302/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 61ms/step - accuracy: 0.2581 - loss: 2.1657[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m153/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 46ms/step - accuracy: 0.1479 - loss: 2.8194[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.1669 - loss: 2.5764 - val_accuracy: 0.1837 - val_loss: 2.3010
[36m(train_cnn_ray_tune pid=1593440)[0m Epoch 11/16
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 112ms/step - accuracy: 0.1562 - loss: 2.7493
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 36ms/step - accuracy: 0.1597 - loss: 2.6373  
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m312/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 61ms/step - accuracy: 0.2581 - loss: 2.1657
[1m313/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 61ms/step - accuracy: 0.2581 - loss: 2.1657
[1m314/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 61ms/step - accuracy: 0.2581 - loss: 2.1657
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m449/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 53ms/step - accuracy: 0.1290 - loss: 2.8082
[1m450/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 53ms/step - accuracy: 0.1290 - loss: 2.8082[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m546/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 32ms/step - accuracy: 0.1474 - loss: 2.6114[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.2491 - loss: 2.1427
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.2490 - loss: 2.1427[32m [repeated 216x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.2016 - loss: 2.1870
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.2016 - loss: 2.1870[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m35s[0m 48ms/step - accuracy: 0.2993 - loss: 1.9475[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.2015 - loss: 2.1870[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m130/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.1765 - loss: 2.5605
[1m132/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.1764 - loss: 2.5603[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m267/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 45ms/step - accuracy: 0.1461 - loss: 2.8187[32m [repeated 145x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m44s[0m 38ms/step - accuracy: 0.1433 - loss: 2.6486 - val_accuracy: 0.1734 - val_loss: 2.3650
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 7/27
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:30[0m 129ms/step - accuracy: 0.2500 - loss: 2.5682
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.2326 - loss: 2.5028  
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 43ms/step - accuracy: 0.2292 - loss: 2.4854
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:58[0m 101ms/step - accuracy: 0.0625 - loss: 2.2037
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 48ms/step - accuracy: 0.1076 - loss: 2.1917  
Trial status: 20 RUNNING
Current time: 2025-10-31 15:09:10. Total running time: 4min 30s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 35ms/step - accuracy: 0.1474 - loss: 2.6104 - val_accuracy: 0.1680 - val_loss: 2.4197
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.1840 - loss: 2.5737  
[1m  6/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 26ms/step - accuracy: 0.1849 - loss: 2.5917
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m420/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 61ms/step - accuracy: 0.2580 - loss: 2.1653 
[1m421/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 61ms/step - accuracy: 0.2580 - loss: 2.1653
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m476/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 60ms/step - accuracy: 0.2009 - loss: 2.4434
[1m477/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 60ms/step - accuracy: 0.2009 - loss: 2.4434[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m486/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 60ms/step - accuracy: 0.2009 - loss: 2.4436
[1m487/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 60ms/step - accuracy: 0.2009 - loss: 2.4436
[1m488/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 60ms/step - accuracy: 0.2009 - loss: 2.4437
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2482 - loss: 2.1434 
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2482 - loss: 2.1434
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2482 - loss: 2.1434
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m565/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 52ms/step - accuracy: 0.1299 - loss: 2.8047[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m29s[0m 56ms/step - accuracy: 0.1412 - loss: 2.7916
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m29s[0m 56ms/step - accuracy: 0.1412 - loss: 2.7916[32m [repeated 218x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.1473 - loss: 2.4799
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.1473 - loss: 2.4799[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m18s[0m 38ms/step - accuracy: 0.1829 - loss: 2.3371[32m [repeated 265x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2481 - loss: 2.1435[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m103/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 30ms/step - accuracy: 0.1592 - loss: 2.5994
[1m105/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 30ms/step - accuracy: 0.1591 - loss: 2.5994[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m259/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 38ms/step - accuracy: 0.1776 - loss: 2.5510[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 44ms/step - accuracy: 0.2016 - loss: 2.1869 - val_accuracy: 0.2068 - val_loss: 2.0800
[36m(train_cnn_ray_tune pid=1593422)[0m Epoch 11/29[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 106ms/step - accuracy: 0.1875 - loss: 2.6447
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 102ms/step - accuracy: 0.3750 - loss: 1.7777
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 50ms/step - accuracy: 0.3750 - loss: 1.7154 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 31/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.4094 - loss: 1.6066
[1m 32/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.4099 - loss: 1.6067
[1m 33/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 43ms/step - accuracy: 0.4105 - loss: 1.6068
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 48ms/step - accuracy: 0.3922 - loss: 1.7112 - val_accuracy: 0.2868 - val_loss: 1.8667[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m318/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1779 - loss: 2.5487 
[1m320/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1779 - loss: 2.5487
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m332/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1780 - loss: 2.5482
[1m334/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.1781 - loss: 2.5481[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 135ms/step - accuracy: 0.0625 - loss: 2.7801
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m462/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 61ms/step - accuracy: 0.2579 - loss: 2.1652
[1m463/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 61ms/step - accuracy: 0.2579 - loss: 2.1652
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 61ms/step - accuracy: 0.2579 - loss: 2.1652
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 74ms/step - accuracy: 0.0859 - loss: 2.8061  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 73ms/step - accuracy: 0.0990 - loss: 2.8179
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 57ms/step - accuracy: 0.1409 - loss: 2.7913
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 57ms/step - accuracy: 0.1409 - loss: 2.7913
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 57ms/step - accuracy: 0.1409 - loss: 2.7913
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m466/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 44ms/step - accuracy: 0.1464 - loss: 2.8135[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m24s[0m 57ms/step - accuracy: 0.1409 - loss: 2.7912
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m24s[0m 57ms/step - accuracy: 0.1409 - loss: 2.7912[32m [repeated 154x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 37ms/step - accuracy: 0.2473 - loss: 2.1438
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 37ms/step - accuracy: 0.2473 - loss: 2.1438[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 38ms/step - accuracy: 0.1821 - loss: 2.3388[32m [repeated 199x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 28ms/step - accuracy: 0.1641 - loss: 2.4978[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m24s[0m 57ms/step - accuracy: 0.1408 - loss: 2.7910
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m23s[0m 57ms/step - accuracy: 0.1408 - loss: 2.7910
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m23s[0m 57ms/step - accuracy: 0.1408 - loss: 2.7910
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m253/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 32ms/step - accuracy: 0.1552 - loss: 2.5941
[1m255/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 32ms/step - accuracy: 0.1552 - loss: 2.5941[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 33/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 57ms/step - accuracy: 0.1461 - loss: 2.7697[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m Epoch 9/28
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 57ms/step - accuracy: 0.1408 - loss: 2.7906
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 57ms/step - accuracy: 0.1408 - loss: 2.7906
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m21s[0m 57ms/step - accuracy: 0.1407 - loss: 2.7906
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 58ms/step - accuracy: 0.1301 - loss: 2.8043 - val_accuracy: 0.1373 - val_loss: 2.5325
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m473/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 37ms/step - accuracy: 0.1794 - loss: 2.5431
[1m475/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 37ms/step - accuracy: 0.1794 - loss: 2.5430[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m381/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1538 - loss: 2.5920[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1565 - loss: 2.5877
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1565 - loss: 2.5877[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 66ms/step - accuracy: 0.1726 - loss: 2.5034 - val_accuracy: 0.2019 - val_loss: 2.1539
[36m(train_cnn_ray_tune pid=1593434)[0m Epoch 7/21
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 113ms/step - accuracy: 0.2812 - loss: 2.3025
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.2422 - loss: 2.3555  
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 36ms/step - accuracy: 0.2409 - loss: 2.1594
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 36ms/step - accuracy: 0.2409 - loss: 2.1593[32m [repeated 143x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m24s[0m 33ms/step - accuracy: 0.1563 - loss: 2.5879[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 37ms/step - accuracy: 0.1812 - loss: 2.3403[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 114ms/step - accuracy: 0.0625 - loss: 2.7362
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.1016 - loss: 2.6009  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 56ms/step - accuracy: 0.1337 - loss: 2.5239
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m144/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 48ms/step - accuracy: 0.1401 - loss: 2.7738
[1m145/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 48ms/step - accuracy: 0.1400 - loss: 2.7738[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 11/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 64ms/step - accuracy: 0.1984 - loss: 2.3812[32m [repeated 132x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m37s[0m 31ms/step - accuracy: 0.1639 - loss: 2.4980 - val_accuracy: 0.1987 - val_loss: 2.2929
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m324/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.4246 - loss: 1.6334 
[1m326/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.4246 - loss: 1.6334
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m523/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 30ms/step - accuracy: 0.1529 - loss: 2.5909
[1m525/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 30ms/step - accuracy: 0.1529 - loss: 2.5909[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m552/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 30ms/step - accuracy: 0.1528 - loss: 2.5906[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 46ms/step - accuracy: 0.3042 - loss: 1.9445
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 46ms/step - accuracy: 0.3042 - loss: 1.9445[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 49ms/step - accuracy: 0.1467 - loss: 2.8111 - val_accuracy: 0.1763 - val_loss: 2.4507[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 11/24[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:57[0m 101ms/step - accuracy: 0.0625 - loss: 2.5833
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 30ms/step - accuracy: 0.0972 - loss: 2.5525  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 57ms/step - accuracy: 0.1406 - loss: 2.7882
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 57ms/step - accuracy: 0.1406 - loss: 2.7882
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 57ms/step - accuracy: 0.1406 - loss: 2.7882
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.3021 - loss: 1.9267  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 36ms/step - accuracy: 0.3038 - loss: 1.9568
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 37ms/step - accuracy: 0.1808 - loss: 2.3411
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 37ms/step - accuracy: 0.1808 - loss: 2.3412[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 26ms/step - accuracy: 0.1491 - loss: 2.4477[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 37ms/step - accuracy: 0.1808 - loss: 2.3412[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:11[0m 112ms/step - accuracy: 0.3125 - loss: 1.8584[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 71ms/step - accuracy: 0.3281 - loss: 2.0999  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 74ms/step - accuracy: 0.3264 - loss: 2.0693
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 10/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 43ms/step - accuracy: 0.2037 - loss: 2.5439
[1m 12/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.2024 - loss: 2.5418[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 89/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m19s[0m 40ms/step - accuracy: 0.1463 - loss: 2.7432[32m [repeated 172x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.2467 - loss: 2.1438 - val_accuracy: 0.2537 - val_loss: 2.1119[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1159 - loss: 2.5863     
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m392/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.3892 - loss: 1.6935
[1m394/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.3892 - loss: 1.6935[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 40ms/step - accuracy: 0.2882 - loss: 1.8444 
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m411/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.3893 - loss: 1.6935[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 37ms/step - accuracy: 0.2571 - loss: 2.0618
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 37ms/step - accuracy: 0.2570 - loss: 2.0618[32m [repeated 177x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 34ms/step - accuracy: 0.1528 - loss: 2.5902 - val_accuracy: 0.1689 - val_loss: 2.4037[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m Epoch 7/29[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:05[0m 108ms/step - accuracy: 0.3750 - loss: 1.7446
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.3281 - loss: 1.8740  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 27ms/step - accuracy: 0.1478 - loss: 2.4448
[1m 222/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 27ms/step - accuracy: 0.1479 - loss: 2.4447
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 27ms/step - accuracy: 0.1479 - loss: 2.4447[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 46ms/step - accuracy: 0.3053 - loss: 1.9428
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 46ms/step - accuracy: 0.3053 - loss: 1.9428
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 46ms/step - accuracy: 0.3053 - loss: 1.9428
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1407 - loss: 2.7863
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1407 - loss: 2.7863[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 27ms/step - accuracy: 0.1668 - loss: 2.5036[32m [repeated 226x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1407 - loss: 2.7862[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:50[0m 95ms/step - accuracy: 0.3125 - loss: 1.4840[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m188/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 59ms/step - accuracy: 0.1810 - loss: 2.4610
[1m189/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 59ms/step - accuracy: 0.1810 - loss: 2.4611[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m207/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m15s[0m 42ms/step - accuracy: 0.1452 - loss: 2.7609[32m [repeated 217x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.3441 - loss: 1.8601 - val_accuracy: 0.3611 - val_loss: 1.7110[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m408/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.1353 - loss: 2.7711
[1m409/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.1353 - loss: 2.7711[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1546 - loss: 2.5915 
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1546 - loss: 2.5915
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m428/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1353 - loss: 2.7709[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 40ms/step - accuracy: 0.2269 - loss: 2.2572
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 41ms/step - accuracy: 0.2264 - loss: 2.2584[32m [repeated 183x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 7/23
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:23[0m 123ms/step - accuracy: 0.2500 - loss: 2.1838
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.2465 - loss: 2.1458  
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 27ms/step - accuracy: 0.1509 - loss: 2.4397
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 27ms/step - accuracy: 0.1509 - loss: 2.4396
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 27ms/step - accuracy: 0.1509 - loss: 2.4396[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 57ms/step - accuracy: 0.1407 - loss: 2.7857
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 57ms/step - accuracy: 0.1407 - loss: 2.7856
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 57ms/step - accuracy: 0.1407 - loss: 2.7856
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.1547 - loss: 2.5917
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.1547 - loss: 2.5917[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 39ms/step - accuracy: 0.2215 - loss: 2.2661[32m [repeated 208x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 57ms/step - accuracy: 0.1407 - loss: 2.7844[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 68[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 37ms/step - accuracy: 0.2550 - loss: 2.0680
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m232/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 59ms/step - accuracy: 0.2747 - loss: 2.1269
[1m233/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 59ms/step - accuracy: 0.2747 - loss: 2.1269[32m [repeated 134x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m270/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 60ms/step - accuracy: 0.1806 - loss: 2.4608[32m [repeated 171x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m49s[0m 42ms/step - accuracy: 0.1807 - loss: 2.3414 - val_accuracy: 0.2041 - val_loss: 2.1276
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m347/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1453 - loss: 2.7638 
[1m349/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1453 - loss: 2.7639
Trial status: 20 RUNNING
Current time: 2025-10-31 15:09:40. Total running time: 5min 0s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 46ms/step - accuracy: 0.4263 - loss: 1.6283 - val_accuracy: 0.3127 - val_loss: 1.8547
[36m(train_cnn_ray_tune pid=1593422)[0m Epoch 12/29
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 105ms/step - accuracy: 0.4375 - loss: 1.5140
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m382/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 43ms/step - accuracy: 0.1453 - loss: 2.7645
[1m384/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 43ms/step - accuracy: 0.1453 - loss: 2.7645[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 33ms/step - accuracy: 0.1547 - loss: 2.5918
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 33ms/step - accuracy: 0.1547 - loss: 2.5918
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 33ms/step - accuracy: 0.1547 - loss: 2.5918
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m530/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 49ms/step - accuracy: 0.1353 - loss: 2.7695[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m28s[0m 37ms/step - accuracy: 0.2566 - loss: 2.0712
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m28s[0m 37ms/step - accuracy: 0.2566 - loss: 2.0712[32m [repeated 196x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.1519 - loss: 2.4384
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.1519 - loss: 2.4384
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.1519 - loss: 2.4383[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 33ms/step - accuracy: 0.1548 - loss: 2.5918
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 33ms/step - accuracy: 0.1548 - loss: 2.5918[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m36s[0m 37ms/step - accuracy: 0.2009 - loss: 2.2863[32m [repeated 217x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 33ms/step - accuracy: 0.1548 - loss: 2.5918[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m356/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 58ms/step - accuracy: 0.2116 - loss: 2.4140
[1m357/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 58ms/step - accuracy: 0.2116 - loss: 2.4140[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m316/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 60ms/step - accuracy: 0.2741 - loss: 2.1265[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 57ms/step - accuracy: 0.3902 - loss: 1.6936 - val_accuracy: 0.3480 - val_loss: 1.8588
[36m(train_cnn_ray_tune pid=1593437)[0m Epoch 10/25
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 101ms/step - accuracy: 0.4062 - loss: 1.4007
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m479/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 38ms/step - accuracy: 0.1826 - loss: 2.5127
[1m481/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 38ms/step - accuracy: 0.1826 - loss: 2.5126[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m414/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.1813 - loss: 2.4581 
[1m415/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.1813 - loss: 2.4581
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m60s[0m 51ms/step - accuracy: 0.3066 - loss: 1.9405 - val_accuracy: 0.3452 - val_loss: 1.7657
[36m(train_cnn_ray_tune pid=1593442)[0m Epoch 6/22
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m549/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 31ms/step - accuracy: 0.1549 - loss: 2.5609[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:58[0m 102ms/step - accuracy: 0.3750 - loss: 1.6373
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.3194 - loss: 1.7738  
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m29s[0m 35ms/step - accuracy: 0.1970 - loss: 2.2929
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m29s[0m 35ms/step - accuracy: 0.1969 - loss: 2.2930[32m [repeated 177x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m27s[0m 36ms/step - accuracy: 0.2678 - loss: 2.0740
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m27s[0m 36ms/step - accuracy: 0.2677 - loss: 2.0741
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m27s[0m 36ms/step - accuracy: 0.2677 - loss: 2.0741
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.1528 - loss: 2.4363
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.1528 - loss: 2.4363[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 36ms/step - accuracy: 0.2562 - loss: 2.0730[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.1671 - loss: 2.4904[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 55ms/step - accuracy: 0.1355 - loss: 2.7681 - val_accuracy: 0.1384 - val_loss: 2.5010
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m407/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 59ms/step - accuracy: 0.2735 - loss: 2.1253
[1m408/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 59ms/step - accuracy: 0.2735 - loss: 2.1253[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m409/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 59ms/step - accuracy: 0.2735 - loss: 2.1253[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 118ms/step - accuracy: 0.0938 - loss: 2.8165
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.1319 - loss: 2.8067  
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 61ms/step - accuracy: 0.1146 - loss: 2.9476
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1172 - loss: 2.9182
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m458/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 58ms/step - accuracy: 0.2732 - loss: 2.1243
[1m459/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 58ms/step - accuracy: 0.2732 - loss: 2.1243[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1187 - loss: 2.8874
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.1181 - loss: 2.8669
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1190 - loss: 2.8499
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.1198 - loss: 2.8328
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m414/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.2107 - loss: 2.4162 
[1m416/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.2107 - loss: 2.4163
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1188 - loss: 2.8252
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.1216 - loss: 2.8094
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.1217 - loss: 2.8035
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 62ms/step - accuracy: 0.1213 - loss: 2.8037
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.1216 - loss: 2.8026
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.1215 - loss: 2.8025
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 37ms/step - accuracy: 0.1549 - loss: 2.5918 - val_accuracy: 0.1785 - val_loss: 2.3418[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 8/27[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m520/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 57ms/step - accuracy: 0.1814 - loss: 2.4565[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.1208 - loss: 2.7983
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.1205 - loss: 2.7982
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.1762 - loss: 2.5475
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 37ms/step - accuracy: 0.1752 - loss: 2.5507[32m [repeated 132x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 94ms/step - accuracy: 0.1875 - loss: 3.1179
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.1198 - loss: 2.7977
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 66ms/step - accuracy: 0.1197 - loss: 2.7968
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 66ms/step - accuracy: 0.1197 - loss: 2.7958
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 66ms/step - accuracy: 0.1195 - loss: 2.7948
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 66ms/step - accuracy: 0.1193 - loss: 2.7935
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 66ms/step - accuracy: 0.1194 - loss: 2.7913
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 26ms/step - accuracy: 0.1530 - loss: 2.4351
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 26ms/step - accuracy: 0.1530 - loss: 2.4351[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 35ms/step - accuracy: 0.1948 - loss: 2.2960[32m [repeated 163x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 26ms/step - accuracy: 0.1530 - loss: 2.4352[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 67ms/step - accuracy: 0.1198 - loss: 2.7860
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 66ms/step - accuracy: 0.1203 - loss: 2.7835
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.1827 - loss: 2.5106 - val_accuracy: 0.1920 - val_loss: 2.2761[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.1220 - loss: 2.7722
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.1221 - loss: 2.7709
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m106/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 47ms/step - accuracy: 0.1479 - loss: 2.6925
[1m108/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 47ms/step - accuracy: 0.1480 - loss: 2.6927[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 14/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 44ms/step - accuracy: 0.1584 - loss: 2.5872[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:15[0m 116ms/step - accuracy: 0.1875 - loss: 2.7131
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.1719 - loss: 2.6428 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.1222 - loss: 2.7698
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.1223 - loss: 2.7688
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.1224 - loss: 2.7676
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.1227 - loss: 2.7655
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.1228 - loss: 2.7646
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.1230 - loss: 2.7639
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.1233 - loss: 2.7614
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.1234 - loss: 2.7606
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.1235 - loss: 2.7597
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.1235 - loss: 2.7588
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.1247 - loss: 2.7545
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.1249 - loss: 2.7539
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  62/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.1251 - loss: 2.7535
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.1252 - loss: 2.7531
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.1258 - loss: 2.7514
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.1261 - loss: 2.7506
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 35ms/step - accuracy: 0.1666 - loss: 2.5768
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 35ms/step - accuracy: 0.1666 - loss: 2.5766
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 35ms/step - accuracy: 0.1667 - loss: 2.5764
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.1265 - loss: 2.7489
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.1266 - loss: 2.7484
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.1276 - loss: 2.7447
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 61ms/step - accuracy: 0.1279 - loss: 2.7436
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m545/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 58ms/step - accuracy: 0.2729 - loss: 2.1229
[1m546/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 58ms/step - accuracy: 0.2729 - loss: 2.1229[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  92/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1289 - loss: 2.7400[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  94/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.1292 - loss: 2.7390
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.1294 - loss: 2.7385
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.1296 - loss: 2.7381
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.1298 - loss: 2.7376
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.1301 - loss: 2.7368
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.1303 - loss: 2.7364
[36m(train_cnn_ray_tune pid=1593440)[0m Epoch 13/16[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m561/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 58ms/step - accuracy: 0.2729 - loss: 2.1226[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 36ms/step - accuracy: 0.2567 - loss: 2.0735
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 36ms/step - accuracy: 0.2567 - loss: 2.0735[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.1318 - loss: 2.7316
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.1320 - loss: 2.7313
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.1321 - loss: 2.7309
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.1322 - loss: 2.7306
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 101ms/step - accuracy: 0.2188 - loss: 2.6140
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.1323 - loss: 2.7303
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.1324 - loss: 2.7299
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.1325 - loss: 2.7296
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 57ms/step - accuracy: 0.1328 - loss: 2.7289
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 26ms/step - accuracy: 0.1523 - loss: 2.4108
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 26ms/step - accuracy: 0.1523 - loss: 2.4108[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 35ms/step - accuracy: 0.1941 - loss: 2.2960[32m [repeated 160x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 26ms/step - accuracy: 0.1523 - loss: 2.4109[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 57ms/step - accuracy: 0.1331 - loss: 2.7282 
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 57ms/step - accuracy: 0.1332 - loss: 2.7280
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m153/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 37ms/step - accuracy: 0.1741 - loss: 2.5254
[1m155/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.1742 - loss: 2.5251[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m281/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 49ms/step - accuracy: 0.4269 - loss: 1.6097[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.1677 - loss: 2.4857 - val_accuracy: 0.2152 - val_loss: 2.2686
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43[0m 88ms/step - accuracy: 0.0625 - loss: 2.4501
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.0807 - loss: 2.4765 
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 65ms/step - accuracy: 0.1815 - loss: 2.4555 - val_accuracy: 0.2067 - val_loss: 2.1413
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1388 - loss: 2.4590
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1382 - loss: 2.4602
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1381 - loss: 2.4607
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 35ms/step - accuracy: 0.3713 - loss: 1.7559
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 35ms/step - accuracy: 0.3713 - loss: 1.7559
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 35ms/step - accuracy: 0.3713 - loss: 1.7559
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 112ms/step - accuracy: 0.2188 - loss: 2.3341
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 70ms/step - accuracy: 0.1875 - loss: 2.3954  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 62ms/step - accuracy: 0.1840 - loss: 2.3909
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m391/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 28ms/step - accuracy: 0.1539 - loss: 2.5474
[1m394/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 28ms/step - accuracy: 0.1539 - loss: 2.5474[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.1329 - loss: 2.7287[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m Epoch 9/20[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m419/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.1541 - loss: 2.5472[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.3706 - loss: 1.7569 
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.3706 - loss: 1.7569
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.1938 - loss: 2.2961
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.1938 - loss: 2.2961[32m [repeated 183x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 35ms/step - accuracy: 0.2670 - loss: 2.0785
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.2670 - loss: 2.0785
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.2670 - loss: 2.0785
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.2571 - loss: 2.0728
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.2571 - loss: 2.0728[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 32ms/step - accuracy: 0.1600 - loss: 2.5774[32m [repeated 183x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 36ms/step - accuracy: 0.2571 - loss: 2.0729[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.2317 - loss: 2.2296 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.2452 - loss: 2.1946
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m291/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.1782 - loss: 2.5125
[1m293/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.1782 - loss: 2.5124[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 43/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 59ms/step - accuracy: 0.1953 - loss: 2.4017[32m [repeated 143x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 44ms/step - accuracy: 0.2253 - loss: 2.1572 - val_accuracy: 0.2427 - val_loss: 2.0129[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 77ms/step - accuracy: 0.2500 - loss: 2.3285
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2188 - loss: 2.3338[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 65ms/step - accuracy: 0.2729 - loss: 2.1220 - val_accuracy: 0.2451 - val_loss: 2.1507[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 25ms/step - accuracy: 0.1426 - loss: 2.4464
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 25ms/step - accuracy: 0.1426 - loss: 2.4464
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 25ms/step - accuracy: 0.1426 - loss: 2.4463
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 135ms/step - accuracy: 0.1875 - loss: 2.2058[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 68ms/step - accuracy: 0.2500 - loss: 2.4097  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 70ms/step - accuracy: 0.2326 - loss: 2.4318
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.1076 - loss: 2.5196 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.1040 - loss: 2.5161
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 63ms/step - accuracy: 0.4375 - loss: 1.4505  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 60ms/step - accuracy: 0.4236 - loss: 1.5057
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m365/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 49ms/step - accuracy: 0.1492 - loss: 2.7003
[1m366/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 49ms/step - accuracy: 0.1492 - loss: 2.7003
[1m367/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 49ms/step - accuracy: 0.1492 - loss: 2.7003
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m564/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.1546 - loss: 2.5462
[1m566/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.1546 - loss: 2.5462[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m Epoch 13/29[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m382/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.1492 - loss: 2.7004[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m50s[0m 57ms/step - accuracy: 0.1389 - loss: 2.7181
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m49s[0m 57ms/step - accuracy: 0.1389 - loss: 2.7180[32m [repeated 159x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 36ms/step - accuracy: 0.2576 - loss: 2.0718
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 36ms/step - accuracy: 0.2576 - loss: 2.0718[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m49s[0m 57ms/step - accuracy: 0.1389 - loss: 2.7178[32m [repeated 194x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 35ms/step - accuracy: 0.1932 - loss: 2.2965[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 92/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m30s[0m 61ms/step - accuracy: 0.2624 - loss: 2.1090
[1m 93/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m30s[0m 62ms/step - accuracy: 0.2625 - loss: 2.1088[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m136/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 60ms/step - accuracy: 0.1848 - loss: 2.4592[32m [repeated 154x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.1525 - loss: 2.4119 - val_accuracy: 0.1774 - val_loss: 2.2580
Trial status: 20 RUNNING
Current time: 2025-10-31 15:10:11. Total running time: 5min 30s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m456/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.1805 - loss: 2.5040
[1m457/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.1805 - loss: 2.5039
[1m459/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.1805 - loss: 2.5038
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 33ms/step - accuracy: 0.1546 - loss: 2.5461 - val_accuracy: 0.1704 - val_loss: 2.3720[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 120ms/step - accuracy: 0.2188 - loss: 2.3902[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m447/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.1549 - loss: 2.7570
[1m449/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.1549 - loss: 2.7570[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 17/29
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m471/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 42ms/step - accuracy: 0.1548 - loss: 2.7564[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m201/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 59ms/step - accuracy: 0.1849 - loss: 2.4508
[1m202/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 59ms/step - accuracy: 0.1849 - loss: 2.4507
[1m203/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 59ms/step - accuracy: 0.1849 - loss: 2.4506
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.1592 - loss: 2.5746
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.1592 - loss: 2.5746[32m [repeated 165x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 35ms/step - accuracy: 0.1928 - loss: 2.2968
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 35ms/step - accuracy: 0.1928 - loss: 2.2968[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 26ms/step - accuracy: 0.1636 - loss: 2.4726[32m [repeated 190x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 35ms/step - accuracy: 0.1928 - loss: 2.2968[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m224/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 59ms/step - accuracy: 0.1852 - loss: 2.4486
[1m225/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 59ms/step - accuracy: 0.1852 - loss: 2.4485[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m217/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 58ms/step - accuracy: 0.2051 - loss: 2.3667[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.2578 - loss: 2.0715 - val_accuracy: 0.2387 - val_loss: 2.1428
[36m(train_cnn_ray_tune pid=1593441)[0m Epoch 7/22
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:25[0m 125ms/step - accuracy: 0.0000e+00 - loss: 2.2656
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 64ms/step - accuracy: 0.0781 - loss: 2.2096     
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.1719 - loss: 2.0559 
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m565/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 42ms/step - accuracy: 0.1545 - loss: 2.7540
[1m567/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 42ms/step - accuracy: 0.1545 - loss: 2.7540[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.1592 - loss: 2.5728
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.1592 - loss: 2.5728
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 33ms/step - accuracy: 0.1592 - loss: 2.5727
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m582/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 49ms/step - accuracy: 0.1489 - loss: 2.7013[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m193/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 61ms/step - accuracy: 0.2696 - loss: 2.0893
[1m194/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 61ms/step - accuracy: 0.2696 - loss: 2.0892
[1m195/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 61ms/step - accuracy: 0.2697 - loss: 2.0891
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 39ms/step - accuracy: 0.2638 - loss: 1.9934
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 39ms/step - accuracy: 0.2629 - loss: 1.9968[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 42ms/step - accuracy: 0.1814 - loss: 2.4990 - val_accuracy: 0.1939 - val_loss: 2.2657
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1926 - loss: 2.2967
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1926 - loss: 2.2967[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m28s[0m 40ms/step - accuracy: 0.2562 - loss: 2.0750[32m [repeated 208x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 35ms/step - accuracy: 0.1926 - loss: 2.2967[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m309/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 57ms/step - accuracy: 0.2071 - loss: 2.3660
[1m311/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 57ms/step - accuracy: 0.2072 - loss: 2.3660[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 14/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 48ms/step - accuracy: 0.4664 - loss: 1.4622[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m314/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 57ms/step - accuracy: 0.2072 - loss: 2.3659
[1m315/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 57ms/step - accuracy: 0.2073 - loss: 2.3659
[1m316/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 57ms/step - accuracy: 0.2073 - loss: 2.3659
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1665 - loss: 2.4668 
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1665 - loss: 2.4668
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.3682 - loss: 1.7590 - val_accuracy: 0.3741 - val_loss: 1.6966[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m Epoch 8/29[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:40[0m 86ms/step - accuracy: 0.2500 - loss: 1.6725
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.3685 - loss: 1.5836 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 121ms/step - accuracy: 0.0938 - loss: 2.9418
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m362/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.4704 - loss: 1.5020
[1m364/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.4704 - loss: 1.5020[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m393/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 41ms/step - accuracy: 0.4705 - loss: 1.5012[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.1465 - loss: 2.4144
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.1466 - loss: 2.4143[32m [repeated 183x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 55ms/step - accuracy: 0.1489 - loss: 2.7013 - val_accuracy: 0.1445 - val_loss: 2.4734[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.1632 - loss: 2.4893  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.1779 - loss: 2.4206
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.1593 - loss: 2.5698
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.1593 - loss: 2.5698[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 35ms/step - accuracy: 0.1950 - loss: 2.3680[32m [repeated 214x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.1674 - loss: 2.4646[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m358/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 58ms/step - accuracy: 0.2762 - loss: 2.0757
[1m359/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 58ms/step - accuracy: 0.2762 - loss: 2.0757[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m403/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 58ms/step - accuracy: 0.1857 - loss: 2.4400[32m [repeated 187x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m315/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 58ms/step - accuracy: 0.2751 - loss: 2.0780
[1m316/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 58ms/step - accuracy: 0.2751 - loss: 2.0780
[1m317/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 58ms/step - accuracy: 0.2751 - loss: 2.0779
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.1926 - loss: 2.2967 - val_accuracy: 0.2167 - val_loss: 2.1008
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 8/23[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:48[0m 144ms/step - accuracy: 0.1250 - loss: 2.5925[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m442/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 57ms/step - accuracy: 0.2091 - loss: 2.3634
[1m443/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 57ms/step - accuracy: 0.2092 - loss: 2.3634[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m413/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.2775 - loss: 2.0733 
[1m414/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.2776 - loss: 2.0733
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m525/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 40ms/step - accuracy: 0.4708 - loss: 1.4987[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 36ms/step - accuracy: 0.2008 - loss: 2.2998
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 36ms/step - accuracy: 0.2007 - loss: 2.2995[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 26ms/step - accuracy: 0.1463 - loss: 2.4339
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 26ms/step - accuracy: 0.1463 - loss: 2.4339[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m28s[0m 35ms/step - accuracy: 0.2758 - loss: 1.9788[32m [repeated 198x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 33ms/step - accuracy: 0.1593 - loss: 2.5680[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 33ms/step - accuracy: 0.1593 - loss: 2.5680
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 33ms/step - accuracy: 0.1593 - loss: 2.5679
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 33ms/step - accuracy: 0.1593 - loss: 2.5679
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m29s[0m 57ms/step - accuracy: 0.1402 - loss: 2.7075
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m29s[0m 57ms/step - accuracy: 0.1403 - loss: 2.7075
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m29s[0m 57ms/step - accuracy: 0.1403 - loss: 2.7075
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m153/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 50ms/step - accuracy: 0.1473 - loss: 2.6941
[1m154/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 50ms/step - accuracy: 0.1473 - loss: 2.6941[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m212/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m15s[0m 42ms/step - accuracy: 0.1648 - loss: 2.7138[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 34ms/step - accuracy: 0.1524 - loss: 2.5258 - val_accuracy: 0.1748 - val_loss: 2.3619
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 18/29
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 93ms/step - accuracy: 0.1562 - loss: 2.2344
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m526/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 58ms/step - accuracy: 0.2099 - loss: 2.3621
[1m527/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 58ms/step - accuracy: 0.2100 - loss: 2.3621[32m [repeated 89x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m504/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 58ms/step - accuracy: 0.2799 - loss: 2.0697[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m Epoch 14/29
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 34ms/step - accuracy: 0.2740 - loss: 2.0301
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 34ms/step - accuracy: 0.2740 - loss: 2.0301[32m [repeated 152x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 109ms/step - accuracy: 0.4375 - loss: 1.3908
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 53ms/step - accuracy: 0.4453 - loss: 1.4023  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 57ms/step - accuracy: 0.4427 - loss: 1.4195
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 45ms/step - accuracy: 0.3343 - loss: 1.8471
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 45ms/step - accuracy: 0.3343 - loss: 1.8471[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m30s[0m 35ms/step - accuracy: 0.1977 - loss: 2.2861[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 27ms/step - accuracy: 0.1486 - loss: 2.4111[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.1687 - loss: 2.4615 - val_accuracy: 0.2128 - val_loss: 2.2547
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 45ms/step - accuracy: 0.3337 - loss: 1.8476
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 45ms/step - accuracy: 0.3337 - loss: 1.8476
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 45ms/step - accuracy: 0.3337 - loss: 1.8476
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m26s[0m 57ms/step - accuracy: 0.1404 - loss: 2.7068
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 57ms/step - accuracy: 0.1404 - loss: 2.7068
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 57ms/step - accuracy: 0.1404 - loss: 2.7068[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1654 - loss: 2.3934 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 28ms/step - accuracy: 0.1799 - loss: 2.3848
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.1007 - loss: 2.3560  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1160 - loss: 2.3428
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 31/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 40ms/step - accuracy: 0.4653 - loss: 1.4301
[1m 33/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 39ms/step - accuracy: 0.4654 - loss: 1.4321[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m268/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 49ms/step - accuracy: 0.1479 - loss: 2.6933[32m [repeated 136x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 73ms/step - accuracy: 0.2578 - loss: 2.4147   
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 45ms/step - accuracy: 0.4711 - loss: 1.4981 - val_accuracy: 0.3684 - val_loss: 1.7924
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44[0m 89ms/step - accuracy: 0.1250 - loss: 2.5249
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.1389 - loss: 2.6147 
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2563 - loss: 2.0665 
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2563 - loss: 2.0665
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2563 - loss: 2.0665
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2563 - loss: 2.0665
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2563 - loss: 2.0665
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m580/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 58ms/step - accuracy: 0.2815 - loss: 2.0671
[1m582/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 58ms/step - accuracy: 0.2815 - loss: 2.0670[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m239/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.1701 - loss: 2.4766 
[1m241/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.1701 - loss: 2.4769
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m416/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 41ms/step - accuracy: 0.1634 - loss: 2.7128[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 9/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m26s[0m 35ms/step - accuracy: 0.1968 - loss: 2.2824
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 35ms/step - accuracy: 0.1968 - loss: 2.2823[32m [repeated 198x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:38:00[0m 16s/step - accuracy: 0.2812 - loss: 2.3425[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 65ms/step - accuracy: 0.1860 - loss: 2.4335 - val_accuracy: 0.2043 - val_loss: 2.1214
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 38ms/step - accuracy: 0.2563 - loss: 2.0660
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 38ms/step - accuracy: 0.2563 - loss: 2.0660[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 30ms/step - accuracy: 0.1759 - loss: 2.5209[32m [repeated 184x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 45ms/step - accuracy: 0.3357 - loss: 1.8456[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 37ms/step - accuracy: 0.1594 - loss: 2.5675 - val_accuracy: 0.1883 - val_loss: 2.3103[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.1350 - loss: 2.6267
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 33ms/step - accuracy: 0.1392 - loss: 2.6217
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.1415 - loss: 2.6093
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m137/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.1980 - loss: 2.4349
[1m139/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.1980 - loss: 2.4352[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m375/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1489 - loss: 2.6916 [32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 24ms/step - accuracy: 0.1591 - loss: 2.3759
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 24ms/step - accuracy: 0.1591 - loss: 2.3760
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 24ms/step - accuracy: 0.1591 - loss: 2.3760
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 157ms/step - accuracy: 0.0938 - loss: 2.6264
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 53ms/step - accuracy: 0.1094 - loss: 2.5210  
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m392/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1490 - loss: 2.6913
[1m393/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1490 - loss: 2.6913
[1m394/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1490 - loss: 2.6913
Trial status: 20 RUNNING
Current time: 2025-10-31 15:10:41. Total running time: 6min 0s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.0972 - loss: 2.4035 
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m424/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1491 - loss: 2.6909
[1m425/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1491 - loss: 2.6909
[1m426/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1491 - loss: 2.6909
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m433/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1491 - loss: 2.6908
[1m435/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.1491 - loss: 2.6907[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m384/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.4265 - loss: 1.5764 
[1m385/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.4265 - loss: 1.5764
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 14/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 55ms/step - accuracy: 0.3349 - loss: 1.9681
[1m 15/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 55ms/step - accuracy: 0.3341 - loss: 1.9703
[1m 16/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 55ms/step - accuracy: 0.3336 - loss: 1.9717
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m448/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 28ms/step - accuracy: 0.1655 - loss: 2.4929[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m Epoch 10/23[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.1955 - loss: 2.2805
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.1955 - loss: 2.2804[32m [repeated 201x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30:11[0m 3s/step - accuracy: 0.1562 - loss: 2.5092[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 65ms/step - accuracy: 0.2816 - loss: 2.0669 - val_accuracy: 0.2479 - val_loss: 2.1516[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 38ms/step - accuracy: 0.2565 - loss: 2.0652
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 38ms/step - accuracy: 0.2565 - loss: 2.0652[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.1955 - loss: 2.2802[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 38ms/step - accuracy: 0.2565 - loss: 2.0652[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.1491 - loss: 2.4098 - val_accuracy: 0.1824 - val_loss: 2.2401
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m274/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.1954 - loss: 2.4464
[1m276/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.1954 - loss: 2.4465[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m295/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 38ms/step - accuracy: 0.4770 - loss: 1.4538[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.2759 - loss: 2.0286
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.2759 - loss: 2.0286
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.2759 - loss: 2.0286[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m59s[0m 50ms/step - accuracy: 0.3359 - loss: 1.8454 - val_accuracy: 0.3454 - val_loss: 1.8043
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:25[0m 125ms/step - accuracy: 0.3750 - loss: 1.6341
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 54ms/step - accuracy: 0.3750 - loss: 1.6932 
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 70ms/step - accuracy: 0.3611 - loss: 1.7474
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.3646 - loss: 1.7725
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 60ms/step - accuracy: 0.3742 - loss: 1.7876
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.3846 - loss: 1.7908
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.3854 - loss: 1.7923
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.3858 - loss: 1.7904
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.3887 - loss: 1.7841 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.3893 - loss: 1.7817
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.3902 - loss: 1.7761 
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m532/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 48ms/step - accuracy: 0.1489 - loss: 2.6896
[1m533/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 48ms/step - accuracy: 0.1489 - loss: 2.6895[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1411 - loss: 2.7048 
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1412 - loss: 2.7048
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m378/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.4790 - loss: 1.4520[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 14/24[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m16s[0m 35ms/step - accuracy: 0.1953 - loss: 2.2786
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m16s[0m 35ms/step - accuracy: 0.1953 - loss: 2.2786[32m [repeated 225x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 106ms/step - accuracy: 0.2500 - loss: 2.4134
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 45ms/step - accuracy: 0.1629 - loss: 2.7104 - val_accuracy: 0.1759 - val_loss: 2.4195
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 35ms/step - accuracy: 0.2736 - loss: 1.9890
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.2736 - loss: 1.9890[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.1953 - loss: 2.2784[32m [repeated 197x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.2736 - loss: 1.9890[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m131/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 60ms/step - accuracy: 0.3185 - loss: 1.9947
[1m132/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 61ms/step - accuracy: 0.3185 - loss: 1.9948[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m120/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 57ms/step - accuracy: 0.2073 - loss: 2.3738[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 33ms/step - accuracy: 0.1644 - loss: 2.4970 - val_accuracy: 0.1761 - val_loss: 2.3454
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 133ms/step - accuracy: 0.1875 - loss: 2.5119
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 25ms/step - accuracy: 0.1584 - loss: 2.3808
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 25ms/step - accuracy: 0.1584 - loss: 2.3808
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 25ms/step - accuracy: 0.1584 - loss: 2.3808
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.1615 - loss: 2.6121  
[1m  6/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.1531 - loss: 2.5842
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m148/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 60ms/step - accuracy: 0.3172 - loss: 1.9961
[1m149/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 60ms/step - accuracy: 0.3172 - loss: 1.9962
[1m150/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 59ms/step - accuracy: 0.3171 - loss: 1.9962
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m50s[0m 43ms/step - accuracy: 0.2565 - loss: 2.0650 - val_accuracy: 0.3036 - val_loss: 1.9182
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.2778 - loss: 1.8343 
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m480/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 37ms/step - accuracy: 0.1940 - loss: 2.4499
[1m482/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 37ms/step - accuracy: 0.1939 - loss: 2.4499[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m497/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 40ms/step - accuracy: 0.4819 - loss: 1.4485[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 48ms/step - accuracy: 0.3649 - loss: 1.8063
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 48ms/step - accuracy: 0.3649 - loss: 1.8064
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 48ms/step - accuracy: 0.3648 - loss: 1.8065
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 57ms/step - accuracy: 0.1415 - loss: 2.7039
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 57ms/step - accuracy: 0.1415 - loss: 2.7039
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 57ms/step - accuracy: 0.1415 - loss: 2.7039
[36m(train_cnn_ray_tune pid=1593436)[0m Epoch 8/21[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 35ms/step - accuracy: 0.1953 - loss: 2.2775
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 35ms/step - accuracy: 0.1953 - loss: 2.2775[32m [repeated 164x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 35ms/step - accuracy: 0.2738 - loss: 1.9891
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 35ms/step - accuracy: 0.2738 - loss: 1.9891[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 48ms/step - accuracy: 0.3637 - loss: 1.8071[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 35ms/step - accuracy: 0.2766 - loss: 2.0261[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m203/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 59ms/step - accuracy: 0.2110 - loss: 2.3563
[1m204/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 59ms/step - accuracy: 0.2110 - loss: 2.3562[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m272/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 58ms/step - accuracy: 0.1787 - loss: 2.4025[32m [repeated 158x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 55ms/step - accuracy: 0.1489 - loss: 2.6889 - val_accuracy: 0.1513 - val_loss: 2.4410[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:20[0m 138ms/step - accuracy: 0.0625 - loss: 2.8484[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m225/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 60ms/step - accuracy: 0.3144 - loss: 1.9982
[1m226/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 60ms/step - accuracy: 0.3144 - loss: 1.9982
[1m227/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 60ms/step - accuracy: 0.3144 - loss: 1.9982[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m579/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.1937 - loss: 2.4489
[1m580/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.1937 - loss: 2.4489[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 38ms/step - accuracy: 0.1937 - loss: 2.4488[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1573 - loss: 2.3848
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1573 - loss: 2.3848
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1573 - loss: 2.3848
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m266/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1613 - loss: 2.5167 
[1m268/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1613 - loss: 2.5166
[36m(train_cnn_ray_tune pid=1593439)[0m Epoch 12/28
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 42ms/step - accuracy: 0.2505 - loss: 2.0129
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 42ms/step - accuracy: 0.2505 - loss: 2.0131[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1954 - loss: 2.2759
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1954 - loss: 2.2759[32m [repeated 152x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m43s[0m 47ms/step - accuracy: 0.3629 - loss: 1.7989[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 36ms/step - accuracy: 0.1954 - loss: 2.2759[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m Epoch 15/29
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m112/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.1395 - loss: 2.6874
[1m113/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.1395 - loss: 2.6873[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m311/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 41ms/step - accuracy: 0.1638 - loss: 2.6782[32m [repeated 202x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 45ms/step - accuracy: 0.4832 - loss: 1.4469 - val_accuracy: 0.3750 - val_loss: 1.8058
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 102ms/step - accuracy: 0.4375 - loss: 1.4657
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m38s[0m 46ms/step - accuracy: 0.3629 - loss: 1.7954
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m38s[0m 46ms/step - accuracy: 0.3629 - loss: 1.7953
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m38s[0m 46ms/step - accuracy: 0.3629 - loss: 1.7953
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m383/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1621 - loss: 2.5128
[1m385/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1621 - loss: 2.5127
[1m387/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1621 - loss: 2.5127
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m46s[0m 39ms/step - accuracy: 0.2738 - loss: 1.9890 - val_accuracy: 0.2466 - val_loss: 2.1226
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42[0m 87ms/step - accuracy: 0.1250 - loss: 1.8098
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m37s[0m 46ms/step - accuracy: 0.3629 - loss: 1.7947
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m37s[0m 46ms/step - accuracy: 0.3629 - loss: 1.7946
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m37s[0m 46ms/step - accuracy: 0.3629 - loss: 1.7946
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m44s[0m 47ms/step - accuracy: 0.1937 - loss: 2.4488 - val_accuracy: 0.1952 - val_loss: 2.2531
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.2639 - loss: 1.7076 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.2890 - loss: 1.7104
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m422/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.1622 - loss: 2.5121
[1m424/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.1622 - loss: 2.5120[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.1560 - loss: 2.3748 
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.1560 - loss: 2.3748
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m398/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 40ms/step - accuracy: 0.1631 - loss: 2.6794[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m407/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.1817 - loss: 2.4007 
[1m409/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.1817 - loss: 2.4007[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m33s[0m 39ms/step - accuracy: 0.2518 - loss: 2.0183
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m33s[0m 39ms/step - accuracy: 0.2518 - loss: 2.0182[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1955 - loss: 2.2737
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1955 - loss: 2.2737[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 37ms/step - accuracy: 0.3078 - loss: 1.8818[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1955 - loss: 2.2737[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 55/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.1909 - loss: 2.4396
[1m 56/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.1908 - loss: 2.4395
[1m 58/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.1905 - loss: 2.4394
[36m(train_cnn_ray_tune pid=1593435)[0m Epoch 9/17[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m224/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 48ms/step - accuracy: 0.1437 - loss: 2.6717
[1m226/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 48ms/step - accuracy: 0.1438 - loss: 2.6716[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 50ms/step - accuracy: 0.4619 - loss: 1.4998[32m [repeated 162x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 54ms/step - accuracy: 0.4844 - loss: 1.6354 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.4440 - loss: 1.6381 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:03[0m 106ms/step - accuracy: 0.1250 - loss: 3.0114
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1406 - loss: 3.0458 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 79ms/step - accuracy: 0.1493 - loss: 3.0170
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m417/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.3109 - loss: 1.9993
[1m418/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.3109 - loss: 1.9993
[1m419/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.3109 - loss: 1.9993
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:26[0m 74ms/step - accuracy: 0.1471 - loss: 2.9934
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 71ms/step - accuracy: 0.1452 - loss: 2.9604
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 68ms/step - accuracy: 0.1453 - loss: 2.9275
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 71ms/step - accuracy: 0.1424 - loss: 2.9051
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 70ms/step - accuracy: 0.1383 - loss: 2.8975
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 68ms/step - accuracy: 0.1353 - loss: 2.8861
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m75s[0m 64ms/step - accuracy: 0.1419 - loss: 2.7028 - val_accuracy: 0.1722 - val_loss: 2.3031[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:24[0m 124ms/step - accuracy: 0.5000 - loss: 1.5686[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 69ms/step - accuracy: 0.1324 - loss: 2.8785
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 68ms/step - accuracy: 0.1307 - loss: 2.8694
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3633 - loss: 1.8086 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.3595 - loss: 1.8123
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 68ms/step - accuracy: 0.1302 - loss: 2.8592
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 67ms/step - accuracy: 0.1302 - loss: 2.8510
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.1298 - loss: 2.8393
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1305 - loss: 2.8283
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1310 - loss: 2.8236
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.1310 - loss: 2.8209
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.1314 - loss: 2.8177
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.1316 - loss: 2.8145
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m446/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 58ms/step - accuracy: 0.3106 - loss: 1.9991
[1m447/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 58ms/step - accuracy: 0.3106 - loss: 1.9991[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1324 - loss: 2.8070
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1327 - loss: 2.8038
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1331 - loss: 2.8009
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1337 - loss: 2.7949
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1337 - loss: 2.7895
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1339 - loss: 2.7863
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1340 - loss: 2.7832
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1340 - loss: 2.7805
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.1340 - loss: 2.7779
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m532/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.1624 - loss: 2.6829[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.1875 - loss: 2.3434  
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.1729 - loss: 2.3748
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.1340 - loss: 2.7762
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1339 - loss: 2.7744
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m411/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.3110 - loss: 1.9993 
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 58ms/step - accuracy: 0.3110 - loss: 1.9993
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1337 - loss: 2.7714
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1337 - loss: 2.7700
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 37ms/step - accuracy: 0.3050 - loss: 1.9115
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m37s[0m 37ms/step - accuracy: 0.3049 - loss: 1.9118[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1337 - loss: 2.7673
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1336 - loss: 2.7660
[1m  42/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1336 - loss: 2.7649
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1335 - loss: 2.7637
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1335 - loss: 2.7628
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1334 - loss: 2.7619
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1334 - loss: 2.7610
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1334 - loss: 2.7603
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1334 - loss: 2.7599
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 27ms/step - accuracy: 0.1550 - loss: 2.3757
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 27ms/step - accuracy: 0.1550 - loss: 2.3757[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 36ms/step - accuracy: 0.4042 - loss: 1.6708[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 31ms/step - accuracy: 0.1712 - loss: 2.5150[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m287/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 48ms/step - accuracy: 0.1450 - loss: 2.6690
[1m288/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 48ms/step - accuracy: 0.1450 - loss: 2.6689
[1m289/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 48ms/step - accuracy: 0.1450 - loss: 2.6689
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.1333 - loss: 2.7598
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.1331 - loss: 2.7597
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.1330 - loss: 2.7597
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.1329 - loss: 2.7597
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.1327 - loss: 2.7598
[36m(train_cnn_ray_tune pid=1593429)[0m Epoch 12/15[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1325 - loss: 2.7599
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1323 - loss: 2.7598
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1323 - loss: 2.7599
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  59/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1322 - loss: 2.7598
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 34ms/step - accuracy: 0.1625 - loss: 2.5093 - val_accuracy: 0.1747 - val_loss: 2.3418
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1322 - loss: 2.7596
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m208/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 37ms/step - accuracy: 0.1855 - loss: 2.4511
[1m209/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 37ms/step - accuracy: 0.1855 - loss: 2.4511[32m [repeated 89x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m369/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 50ms/step - accuracy: 0.4611 - loss: 1.5027[32m [repeated 127x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1321 - loss: 2.7595
[1m  63/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1321 - loss: 2.7590
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 56ms/step - accuracy: 0.2031 - loss: 2.1684 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.1846 - loss: 2.2532 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1322 - loss: 2.7585
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.1323 - loss: 2.7576
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.1323 - loss: 2.7571
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.1324 - loss: 2.7565
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1324 - loss: 2.7561
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1325 - loss: 2.7555
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.1326 - loss: 2.7549
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.1327 - loss: 2.7543
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.1327 - loss: 2.7537
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.1327 - loss: 2.7530
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 52ms/step - accuracy: 0.2188 - loss: 2.4168 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.2435 - loss: 2.2818 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.1329 - loss: 2.7516
Trial status: 20 RUNNING
Current time: 2025-10-31 15:11:11. Total running time: 6min 30s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.1329 - loss: 2.7510
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1330 - loss: 2.7503
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1330 - loss: 2.7497
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1330 - loss: 2.7492
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.1331 - loss: 2.7486
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.1332 - loss: 2.7480
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.1333 - loss: 2.7474
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.1333 - loss: 2.7468
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 92ms/step - accuracy: 0.2812 - loss: 2.4312
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 31ms/step - accuracy: 0.2274 - loss: 2.4815
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m316/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.5119 - loss: 1.3721 
[1m318/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.5120 - loss: 1.3721
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.1334 - loss: 2.7462
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1335 - loss: 2.7455
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  87/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1335 - loss: 2.7450
[1m  88/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1336 - loss: 2.7444
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  89/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1337 - loss: 2.7438
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  90/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1338 - loss: 2.7432
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1338 - loss: 2.7426
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  92/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1339 - loss: 2.7421
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  93/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1340 - loss: 2.7415
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  94/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1341 - loss: 2.7409
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1341 - loss: 2.7404
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.1955 - loss: 2.2736 - val_accuracy: 0.2500 - val_loss: 2.0728[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:05[0m 159ms/step - accuracy: 0.1875 - loss: 2.5529[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1342 - loss: 2.7399
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1343 - loss: 2.7394
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1343 - loss: 2.7389
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1344 - loss: 2.7383
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m271/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.1860 - loss: 2.4486
[1m273/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.1860 - loss: 2.4485
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.1861 - loss: 2.4484
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1345 - loss: 2.7378
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1346 - loss: 2.7372
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.1346 - loss: 2.7366
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.1347 - loss: 2.7361
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1347 - loss: 2.7356
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m531/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 58ms/step - accuracy: 0.3100 - loss: 1.9986
[1m532/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 58ms/step - accuracy: 0.3100 - loss: 1.9986[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1349 - loss: 2.7347
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.1349 - loss: 2.7342
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.1350 - loss: 2.7337
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.1350 - loss: 2.7332
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.1351 - loss: 2.7322
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.1352 - loss: 2.7317
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.1352 - loss: 2.7312
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.1353 - loss: 2.7307
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.1354 - loss: 2.7297
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.1354 - loss: 2.7291
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m544/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 58ms/step - accuracy: 0.3100 - loss: 1.9985[32m [repeated 144x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 118/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.1355 - loss: 2.7286
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.1356 - loss: 2.7276
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 34ms/step - accuracy: 0.3016 - loss: 1.9319
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 34ms/step - accuracy: 0.3016 - loss: 1.9320[32m [repeated 173x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 26ms/step - accuracy: 0.1652 - loss: 2.3724
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 26ms/step - accuracy: 0.1651 - loss: 2.3723
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 26ms/step - accuracy: 0.1651 - loss: 2.3722
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.1357 - loss: 2.7271
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.1358 - loss: 2.7261
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.1359 - loss: 2.7256
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.1360 - loss: 2.7252
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.1361 - loss: 2.7248
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.1361 - loss: 2.7243
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 60ms/step - accuracy: 0.1362 - loss: 2.7239
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.1363 - loss: 2.7235
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.1364 - loss: 2.7231
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.1365 - loss: 2.7227
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.1711 - loss: 2.5143
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.1711 - loss: 2.5143[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 37ms/step - accuracy: 0.2141 - loss: 2.2087[32m [repeated 206x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 32ms/step - accuracy: 0.1711 - loss: 2.5143[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.1366 - loss: 2.7223
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.1367 - loss: 2.7219
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.1369 - loss: 2.7212
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.1369 - loss: 2.7208
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.1370 - loss: 2.7205
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.1371 - loss: 2.7201
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 15/24[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 140/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1372 - loss: 2.7194
[1m 141/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1373 - loss: 2.7191
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1374 - loss: 2.7183
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 144/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1375 - loss: 2.7179
[1m 145/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1376 - loss: 2.7176
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 46ms/step - accuracy: 0.1624 - loss: 2.6837 - val_accuracy: 0.1802 - val_loss: 2.4093
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 146/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1377 - loss: 2.7172
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.1673 - loss: 2.4936
[1m170/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.1672 - loss: 2.4935[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 26/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 46ms/step - accuracy: 0.1633 - loss: 2.6290[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1378 - loss: 2.7164
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1379 - loss: 2.7159
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1380 - loss: 2.7155
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1380 - loss: 2.7151
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1381 - loss: 2.7147
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.1381 - loss: 2.7143
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 59ms/step - accuracy: 0.1382 - loss: 2.7136 
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 29ms/step - accuracy: 0.2674 - loss: 2.2510  
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m37s[0m 64ms/step - accuracy: 0.1839 - loss: 2.3994 - val_accuracy: 0.2139 - val_loss: 2.1091
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m313/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1864 - loss: 2.4473 
[1m315/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1864 - loss: 2.4473[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 137ms/step - accuracy: 0.1875 - loss: 2.2144
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 44ms/step - accuracy: 0.1823 - loss: 2.3246  
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.1546 - loss: 2.3762 - val_accuracy: 0.1741 - val_loss: 2.2313
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:10[0m 112ms/step - accuracy: 0.2500 - loss: 2.2270[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 36ms/step - accuracy: 0.1711 - loss: 2.5143 - val_accuracy: 0.1841 - val_loss: 2.2980
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m267/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.1645 - loss: 2.4899
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.1644 - loss: 2.4898[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m444/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1867 - loss: 2.4442[32m [repeated 142x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 223/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 36ms/step - accuracy: 0.2161 - loss: 2.2260
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 36ms/step - accuracy: 0.2161 - loss: 2.2260[32m [repeated 243x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m57s[0m 59ms/step - accuracy: 0.1399 - loss: 2.7030
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m57s[0m 59ms/step - accuracy: 0.1399 - loss: 2.7028
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m57s[0m 59ms/step - accuracy: 0.1400 - loss: 2.7026
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m55s[0m 58ms/step - accuracy: 0.1409 - loss: 2.6985
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m55s[0m 58ms/step - accuracy: 0.1410 - loss: 2.6983
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m55s[0m 58ms/step - accuracy: 0.1410 - loss: 2.6981
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m55s[0m 59ms/step - accuracy: 0.1414 - loss: 2.6967[32m [repeated 204x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 10/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 62/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 56ms/step - accuracy: 0.2003 - loss: 2.3842
[1m 64/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 55ms/step - accuracy: 0.2003 - loss: 2.3834[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 65/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 55ms/step - accuracy: 0.2002 - loss: 2.3831[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 65ms/step - accuracy: 0.2158 - loss: 2.3397 - val_accuracy: 0.2368 - val_loss: 2.1988[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 106ms/step - accuracy: 0.0938 - loss: 2.3305
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 53ms/step - accuracy: 0.1484 - loss: 2.2411  [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m439/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 29ms/step - accuracy: 0.1636 - loss: 2.4873
[1m441/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 29ms/step - accuracy: 0.1636 - loss: 2.4873[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m572/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.1874 - loss: 2.4409[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2991 - loss: 1.9285
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2991 - loss: 1.9285[32m [repeated 281x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 97ms/step - accuracy: 0.5000 - loss: 1.5866
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 27ms/step - accuracy: 0.1633 - loss: 2.3613[32m [repeated 259x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m Epoch 13/25[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.1599 - loss: 2.3706
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.1599 - loss: 2.3706
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.1599 - loss: 2.3706
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 74/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 61ms/step - accuracy: 0.3328 - loss: 1.9212
[1m 75/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 61ms/step - accuracy: 0.3328 - loss: 1.9212[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m153/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 56ms/step - accuracy: 0.1953 - loss: 2.3652[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 55ms/step - accuracy: 0.1472 - loss: 2.6600 - val_accuracy: 0.1574 - val_loss: 2.4156[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2595 - loss: 2.0161
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2595 - loss: 2.0161
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.1493 - loss: 2.6275  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.1571 - loss: 2.5943
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2596 - loss: 2.0161
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2596 - loss: 2.0160
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2596 - loss: 2.0160
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2596 - loss: 2.0160
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2596 - loss: 2.0160
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2596 - loss: 2.0160
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2596 - loss: 2.0160
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2596 - loss: 2.0160
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2597 - loss: 2.0160
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2597 - loss: 2.0160
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2597 - loss: 2.0160
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m578/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.1640 - loss: 2.4852
[1m581/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.1640 - loss: 2.4852[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1767 - loss: 2.4058 
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1767 - loss: 2.4058
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2597 - loss: 2.0159
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2597 - loss: 2.0159
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2597 - loss: 2.0159
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m348/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1594 - loss: 2.6533 
[1m349/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1594 - loss: 2.6533
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m583/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.1640 - loss: 2.4852[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.2987 - loss: 1.9279
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.2987 - loss: 1.9279[32m [repeated 221x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 48/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 58ms/step - accuracy: 0.1415 - loss: 2.6130
[1m 49/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 58ms/step - accuracy: 0.1418 - loss: 2.6127
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 58ms/step - accuracy: 0.1420 - loss: 2.6125
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 119ms/step - accuracy: 0.1562 - loss: 2.6322[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 36ms/step - accuracy: 0.2178 - loss: 2.2296[32m [repeated 277x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m Epoch 16/16[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 46ms/step - accuracy: 0.3658 - loss: 1.7794
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 46ms/step - accuracy: 0.3658 - loss: 1.7793
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 46ms/step - accuracy: 0.3658 - loss: 1.7793[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 69/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 56ms/step - accuracy: 0.1443 - loss: 2.6095
[1m 70/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 56ms/step - accuracy: 0.1444 - loss: 2.6092[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m157/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m26s[0m 62ms/step - accuracy: 0.3307 - loss: 1.9206[32m [repeated 223x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 34ms/step - accuracy: 0.1640 - loss: 2.4852 - val_accuracy: 0.1765 - val_loss: 2.3283[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 46ms/step - accuracy: 0.3660 - loss: 1.7776
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 46ms/step - accuracy: 0.3660 - loss: 1.7776[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 46ms/step - accuracy: 0.3660 - loss: 1.7776[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m441/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 43ms/step - accuracy: 0.1604 - loss: 2.6538
[1m443/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 43ms/step - accuracy: 0.1604 - loss: 2.6539[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.3659 - loss: 1.7782 
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.3659 - loss: 1.7782
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m457/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 43ms/step - accuracy: 0.1605 - loss: 2.6541[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2174 - loss: 2.2310
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2174 - loss: 2.2310[32m [repeated 181x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 77ms/step - accuracy: 0.2188 - loss: 2.5780
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m149/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 54ms/step - accuracy: 0.1490 - loss: 2.6000
[1m150/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 54ms/step - accuracy: 0.1490 - loss: 2.6000
[1m151/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 54ms/step - accuracy: 0.1491 - loss: 2.6001
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2173 - loss: 2.2311[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 21/29
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.4002 - loss: 1.6676
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.4003 - loss: 1.6676
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.4003 - loss: 1.6676
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m215/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 39ms/step - accuracy: 0.1900 - loss: 2.4541
[1m217/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 39ms/step - accuracy: 0.1900 - loss: 2.4539[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m241/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 43ms/step - accuracy: 0.5298 - loss: 1.3151[32m [repeated 219x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2981 - loss: 1.9266 
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2981 - loss: 1.9266
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.1773 - loss: 2.4060
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.1773 - loss: 2.4060
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.1773 - loss: 2.4059
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2981 - loss: 1.9263
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 38ms/step - accuracy: 0.2981 - loss: 1.9263[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.2614 - loss: 2.0148[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m551/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 43ms/step - accuracy: 0.1610 - loss: 2.6549
[1m552/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 43ms/step - accuracy: 0.1610 - loss: 2.6549[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m565/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 44ms/step - accuracy: 0.1610 - loss: 2.6551[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m273/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1693 - loss: 2.4791 
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1693 - loss: 2.4791
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 37ms/step - accuracy: 0.2168 - loss: 2.2316
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 37ms/step - accuracy: 0.2168 - loss: 2.2317[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m14s[0m 37ms/step - accuracy: 0.2167 - loss: 2.2318[32m [repeated 140x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m267/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 52ms/step - accuracy: 0.1512 - loss: 2.6020
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 52ms/step - accuracy: 0.1512 - loss: 2.6021[32m [repeated 152x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m316/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 63ms/step - accuracy: 0.3290 - loss: 1.9217[32m [repeated 216x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-10-31 15:11:41. Total running time: 7min 0s
Logical resource usage: 20.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status       N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25 │
│ trial_8b084    RUNNING            2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 16                  3                 1          0.000172735         21 │
│ trial_8b084    RUNNING            2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 64                  3                 0          0.000176203         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28 │
│ trial_8b084    RUNNING            3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22 │
│ trial_8b084    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22 │
│ trial_8b084    RUNNING            3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23 │
│ trial_8b084    RUNNING            2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27 │
│ trial_8b084    RUNNING            2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15 │
│ trial_8b084    RUNNING            2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.4005 - loss: 1.6650
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.4005 - loss: 1.6650
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.4005 - loss: 1.6650
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 38ms/step - accuracy: 0.2980 - loss: 1.9252
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 38ms/step - accuracy: 0.2980 - loss: 1.9252[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 36ms/step - accuracy: 0.2988 - loss: 1.9432[32m [repeated 154x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 49ms/step - accuracy: 0.1610 - loss: 2.6554 - val_accuracy: 0.1813 - val_loss: 2.4000
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 16/24
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 107ms/step - accuracy: 0.2500 - loss: 2.4149
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 29ms/step - accuracy: 0.1591 - loss: 2.3722 - val_accuracy: 0.2052 - val_loss: 2.1895
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 79ms/step - accuracy: 0.1250 - loss: 2.5449
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.1181 - loss: 2.4961 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m31s[0m 58ms/step - accuracy: 0.1494 - loss: 2.6603
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m31s[0m 58ms/step - accuracy: 0.1495 - loss: 2.6602
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m31s[0m 58ms/step - accuracy: 0.1495 - loss: 2.6601
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m455/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 58ms/step - accuracy: 0.1943 - loss: 2.3529
[1m456/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 58ms/step - accuracy: 0.1943 - loss: 2.3529[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.1528 - loss: 2.7304 
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m466/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 58ms/step - accuracy: 0.1944 - loss: 2.3526[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.2162 - loss: 2.2325
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.2161 - loss: 2.2325[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2161 - loss: 2.2325 
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2161 - loss: 2.2325
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m30s[0m 58ms/step - accuracy: 0.1497 - loss: 2.6585[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m406/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 60ms/step - accuracy: 0.2236 - loss: 2.3089
[1m407/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 60ms/step - accuracy: 0.2236 - loss: 2.3089[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 72/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 41ms/step - accuracy: 0.1669 - loss: 2.6587[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m424/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 62ms/step - accuracy: 0.3284 - loss: 1.9222 
[1m425/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 62ms/step - accuracy: 0.3284 - loss: 1.9222
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 27ms/step - accuracy: 0.1569 - loss: 2.3666
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.1569 - loss: 2.3666[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.1569 - loss: 2.3666[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m Epoch 13/25[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44[0m 90ms/step - accuracy: 0.1875 - loss: 2.8987
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 31ms/step - accuracy: 0.1775 - loss: 2.4057 - val_accuracy: 0.2144 - val_loss: 2.2306[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:08[0m 110ms/step - accuracy: 0.1250 - loss: 2.1473
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.1528 - loss: 2.1151  
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:20[0m 121ms/step - accuracy: 0.5625 - loss: 1.2894
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 57ms/step - accuracy: 0.5312 - loss: 1.3561 
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.5000 - loss: 1.4386
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.4805 - loss: 1.4725
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m543/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.1954 - loss: 2.4262
[1m545/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.1954 - loss: 2.4261[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.4533 - loss: 1.5179 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 50ms/step - accuracy: 0.4421 - loss: 1.5369
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 60ms/step - accuracy: 0.2240 - loss: 2.3067[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 58ms/step - accuracy: 0.1504 - loss: 2.6542
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 58ms/step - accuracy: 0.1504 - loss: 2.6542[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m23s[0m 26ms/step - accuracy: 0.1767 - loss: 2.4022[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m188/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m16s[0m 42ms/step - accuracy: 0.1637 - loss: 2.6712
[1m190/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m16s[0m 42ms/step - accuracy: 0.1638 - loss: 2.6712[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m178/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 43ms/step - accuracy: 0.1635 - loss: 2.6712[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 35ms/step - accuracy: 0.1667 - loss: 2.4773 - val_accuracy: 0.1815 - val_loss: 2.3173
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:24[0m 72ms/step - accuracy: 0.1875 - loss: 1.7168
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 35ms/step - accuracy: 0.3646 - loss: 1.7918  
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 37ms/step - accuracy: 0.2156 - loss: 2.2322
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 37ms/step - accuracy: 0.2156 - loss: 2.2322[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 37ms/step - accuracy: 0.2156 - loss: 2.2322[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m Epoch 10/29[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.4011 - loss: 1.6600 - val_accuracy: 0.3874 - val_loss: 1.6770[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 370ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 5/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step  
[1m 9/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.1562 - loss: 2.4508
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 21ms/step - accuracy: 0.1667 - loss: 2.4185
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m13/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m17/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 25ms/step - accuracy: 0.1782 - loss: 2.3951
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 25ms/step - accuracy: 0.1783 - loss: 2.3950
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 25ms/step - accuracy: 0.1783 - loss: 2.3950
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[1m24/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m530/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 61ms/step - accuracy: 0.3281 - loss: 1.9227
[1m531/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 61ms/step - accuracy: 0.3281 - loss: 1.9227[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.2465 - loss: 1.6980 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 30ms/step - accuracy: 0.2891 - loss: 1.7251[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m28/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m32/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m38/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m45/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 14ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 14ms/step
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 14ms/step
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m543/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 61ms/step - accuracy: 0.3280 - loss: 1.9227[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[1m78/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m81/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[1m84/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m20s[0m 58ms/step - accuracy: 0.1510 - loss: 2.6495
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m20s[0m 58ms/step - accuracy: 0.1510 - loss: 2.6495[32m [repeated 168x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 19ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 34ms/step - accuracy: 0.3167 - loss: 1.8177[32m [repeated 151x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 76ms/step
[1m  4/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step 
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m  8/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 12/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 17/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 20/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 24/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 27/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 32/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 36/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 39/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 42/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 47/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 51/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 54/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m171/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 29ms/step - accuracy: 0.1685 - loss: 2.4446
[1m174/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 29ms/step - accuracy: 0.1685 - loss: 2.4446[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m169/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.1685 - loss: 2.4446[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593440)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:44.183243: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:44.205545: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m WARNING: All log messages before absl::InitializeLog() is called are written to STDERR[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m E0000 00:00:1761919484.234605 1594708 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m E0000 00:00:1761919484.242886 1594708 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m W0000 00:00:1761919484.264125 1594708 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:44.270458: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:47.656788: E external/local_xla/xla/stream_executor/cuda/cuda_platform.cc:51] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:47.656886: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:167] env: CUDA_VISIBLE_DEVICES=""[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:47.656899: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:170] CUDA_VISIBLE_DEVICES is set to an empty string - this hides all GPUs from CUDA[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:47.656905: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:178] verbose logging is disabled. Rerun with verbose logging (usually --v=1 or --vmodule=cuda_diagnostics=1) to get more diagnostic output from this module[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:47.656910: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:183] retrieving CUDA diagnostic information for host: simur-MS-7B94[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:47.656913: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:190] hostname: simur-MS-7B94[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:47.657372: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:197] libcuda reported version is: 570.133.7[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:47.657433: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:201] kernel reported version is: 570.133.7[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 2025-10-31 15:04:47.657438: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:291] kernel version seems to match DSO: 570.133.7[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 66ms/step - accuracy: 0.1947 - loss: 2.3512 - val_accuracy: 0.2170 - val_loss: 2.0949[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 56/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 59/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 63/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 67/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 70/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 74/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 77/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 81/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 85/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 90/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 94/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m 99/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m103/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m107/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m114/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m119/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[1m123/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m127/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[1m132/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 119ms/step - accuracy: 0.3750 - loss: 1.8206[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m137/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[1m141/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m143/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[1m146/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m149/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[1m155/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m158/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[1m162/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593440)[0m 
[1m167/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 15ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:11:57. Total running time: 7min 17s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             434.114 │
│ time_total_s                 434.114 │
│ training_iteration                 1 │
│ val_accuracy                 0.19204 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:11:57. Total running time: 7min 17s
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.1774 - loss: 2.4826
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.1774 - loss: 2.4826[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.1774 - loss: 2.4826[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m Epoch 11/21[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 422ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 5/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step  
[1m 8/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m11/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 18ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m21s[0m 58ms/step - accuracy: 0.1509 - loss: 2.6503
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m20s[0m 58ms/step - accuracy: 0.1509 - loss: 2.6503
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m20s[0m 58ms/step - accuracy: 0.1509 - loss: 2.6502
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 18ms/step
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 18ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 41ms/step - accuracy: 0.1667 - loss: 2.6648
[1m378/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 41ms/step - accuracy: 0.1667 - loss: 2.6648[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m24/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 18ms/step
[1m27/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 18ms/step
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.2155 - loss: 2.2320 - val_accuracy: 0.2775 - val_loss: 2.0483
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 18ms/step
[1m34/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 18ms/step
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 65ms/step - accuracy: 0.1250 - loss: 2.7135
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.1602 - loss: 2.4288 
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m38/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 18ms/step
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 18ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 24ms/step - accuracy: 0.1483 - loss: 2.3690
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 24ms/step - accuracy: 0.1484 - loss: 2.3689
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 24ms/step - accuracy: 0.1484 - loss: 2.3688
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m45/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 18ms/step
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 18ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m49/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m297/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 28ms/step - accuracy: 0.1677 - loss: 2.4455[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 20ms/step
[1m57/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 20ms/step
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m31s[0m 33ms/step - accuracy: 0.3191 - loss: 1.8344
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m31s[0m 33ms/step - accuracy: 0.3191 - loss: 1.8345[32m [repeated 245x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 20ms/step
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 20ms/step
[1m76/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m80/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m84/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m13s[0m 57ms/step - accuracy: 0.1518 - loss: 2.6444[32m [repeated 207x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 24ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 24ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 57ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m  4/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 28ms/step
[1m  8/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 12/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 18ms/step
[1m 15/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 71ms/step - accuracy: 0.4531 - loss: 1.7664
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 71ms/step - accuracy: 0.4236 - loss: 1.8086[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m216/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 37ms/step - accuracy: 0.5421 - loss: 1.2972[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 68ms/step - accuracy: 0.3280 - loss: 1.9227 - val_accuracy: 0.2490 - val_loss: 2.1676[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 18/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step
[1m 21/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 24/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 27/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 30/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 34/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 36/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 39/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.1736 - loss: 2.4406 
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 43/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[1m 47/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 49/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 58/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 61/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 64/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 67/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 70/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:52[0m 97ms/step - accuracy: 0.1875 - loss: 2.4348[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 20ms/step
[1m 77/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 81/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 20ms/step
[1m 83/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 85/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 20ms/step
[1m 88/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 91/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 20ms/step
[1m 95/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.1550 - loss: 2.3566 
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.1550 - loss: 2.3565
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m 98/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 20ms/step
[1m100/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.1551 - loss: 2.3565
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.1551 - loss: 2.3565[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m104/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 20ms/step
[1m107/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.1792 - loss: 2.3895[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m109/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 20ms/step
[1m112/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 11/27[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m115/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 21ms/step
[1m118/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m121/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m124/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 20ms/step
[1m127/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m130/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 20ms/step
[1m133/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m137/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 20ms/step
[1m141/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m145/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 20ms/step
[1m149/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m152/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m446/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 28ms/step - accuracy: 0.1680 - loss: 2.4485
[1m449/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 28ms/step - accuracy: 0.1680 - loss: 2.4485[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m154/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 20ms/step
[1m157/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m161/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m165/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 37ms/step - accuracy: 0.1774 - loss: 2.4826 - val_accuracy: 0.1837 - val_loss: 2.2766
[36m(train_cnn_ray_tune pid=1593437)[0m 
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 91ms/step - accuracy: 0.0938 - loss: 2.7385
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 40ms/step - accuracy: 0.1441 - loss: 2.5498[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m25s[0m 37ms/step - accuracy: 0.2904 - loss: 1.9828
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m25s[0m 37ms/step - accuracy: 0.2904 - loss: 1.9828
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m25s[0m 37ms/step - accuracy: 0.2904 - loss: 1.9827

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:12:03. Total running time: 7min 23s
[36m(train_cnn_ray_tune pid=1593437)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593437)[0m   _log_deprecation_warning(
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             440.267 │
│ time_total_s                 440.267 │
│ training_iteration                 1 │
│ val_accuracy                 0.36596 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:12:03. Total running time: 7min 23s
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m467/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 28ms/step - accuracy: 0.1680 - loss: 2.4488[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 35ms/step - accuracy: 0.1757 - loss: 2.4630
[1m  93/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 35ms/step - accuracy: 0.1757 - loss: 2.4627
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 35ms/step - accuracy: 0.1757 - loss: 2.4625
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m27s[0m 34ms/step - accuracy: 0.3186 - loss: 1.8359
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m27s[0m 34ms/step - accuracy: 0.3186 - loss: 1.8359[32m [repeated 232x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m27s[0m 34ms/step - accuracy: 0.3184 - loss: 1.8362[32m [repeated 228x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m103/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 58ms/step - accuracy: 0.2320 - loss: 2.2795
[1m104/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 58ms/step - accuracy: 0.2321 - loss: 2.2793[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 90/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m28s[0m 58ms/step - accuracy: 0.3347 - loss: 1.8813[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m120/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 59ms/step - accuracy: 0.2328 - loss: 2.2763
[1m121/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 59ms/step - accuracy: 0.2328 - loss: 2.2762
[1m122/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 59ms/step - accuracy: 0.2329 - loss: 2.2760
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 24ms/step - accuracy: 0.1797 - loss: 2.3872
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 24ms/step - accuracy: 0.1797 - loss: 2.3872[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 24ms/step - accuracy: 0.1797 - loss: 2.3872[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m144/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m25s[0m 58ms/step - accuracy: 0.2334 - loss: 2.2740
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 57ms/step - accuracy: 0.1529 - loss: 2.6393
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 57ms/step - accuracy: 0.1529 - loss: 2.6393
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 57ms/step - accuracy: 0.1529 - loss: 2.6393
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m412/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 38ms/step - accuracy: 0.5446 - loss: 1.2908
[1m413/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 38ms/step - accuracy: 0.5446 - loss: 1.2908[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m428/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 38ms/step - accuracy: 0.5446 - loss: 1.2903[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 34ms/step - accuracy: 0.3176 - loss: 1.8378
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 34ms/step - accuracy: 0.3176 - loss: 1.8378
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 34ms/step - accuracy: 0.3176 - loss: 1.8378[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 34ms/step - accuracy: 0.3130 - loss: 1.8952
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 34ms/step - accuracy: 0.3130 - loss: 1.8952[32m [repeated 188x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 46ms/step - accuracy: 0.1676 - loss: 2.6600 - val_accuracy: 0.1821 - val_loss: 2.3885
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 17/24
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 126ms/step - accuracy: 0.1875 - loss: 2.7430
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  2/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.1875 - loss: 2.7411  
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 55ms/step - accuracy: 0.1944 - loss: 2.7162
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m28s[0m 43ms/step - accuracy: 0.3773 - loss: 1.7007[32m [repeated 204x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m183/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 56ms/step - accuracy: 0.3434 - loss: 1.8697
[1m184/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 56ms/step - accuracy: 0.3435 - loss: 1.8697[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m197/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 56ms/step - accuracy: 0.2337 - loss: 2.2719[32m [repeated 128x across cluster][0m

Trial status: 18 RUNNING | 2 TERMINATED
Current time: 2025-10-31 15:12:11. Total running time: 7min 30s
Logical resource usage: 18.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24                                              │
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25                                              │
│ trial_8b084    RUNNING              2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18                                              │
│ trial_8b084    RUNNING              2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 16                  3                 1          0.000172735         21                                              │
│ trial_8b084    RUNNING              3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 64                  3                 0          0.000176203         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    RUNNING              3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27                                              │
│ trial_8b084    RUNNING              2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15                                              │
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17                                              │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 57ms/step - accuracy: 0.1532 - loss: 2.6374
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 57ms/step - accuracy: 0.1533 - loss: 2.6374[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 25ms/step - accuracy: 0.1552 - loss: 2.3554[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 25ms/step - accuracy: 0.1574 - loss: 2.3546
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 25ms/step - accuracy: 0.1574 - loss: 2.3546
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 25ms/step - accuracy: 0.1574 - loss: 2.3546[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m545/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 37ms/step - accuracy: 0.5456 - loss: 1.2860
[1m547/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 37ms/step - accuracy: 0.5456 - loss: 1.2859[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m569/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.5457 - loss: 1.2853[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m22s[0m 33ms/step - accuracy: 0.2064 - loss: 2.2001
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m22s[0m 33ms/step - accuracy: 0.2064 - loss: 2.2001[32m [repeated 192x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 33ms/step - accuracy: 0.1678 - loss: 2.4501 - val_accuracy: 0.1796 - val_loss: 2.3108
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 23/29
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 75ms/step - accuracy: 0.2188 - loss: 2.5282
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.3145 - loss: 1.8962[32m [repeated 153x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 28ms/step - accuracy: 0.1796 - loss: 2.3867 - val_accuracy: 0.2011 - val_loss: 2.2235
[36m(train_cnn_ray_tune pid=1593421)[0m Epoch 14/25
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:23[0m 72ms/step - accuracy: 0.3125 - loss: 2.3676
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 17ms/step - accuracy: 0.2396 - loss: 2.3496 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2284 - loss: 2.3421
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m285/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 53ms/step - accuracy: 0.3464 - loss: 1.8668
[1m287/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 53ms/step - accuracy: 0.3464 - loss: 1.8668[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m361/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 47ms/step - accuracy: 0.1636 - loss: 2.6098[32m [repeated 143x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m369/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.1636 - loss: 2.6095 
[1m371/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.1636 - loss: 2.6094
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1576 - loss: 2.0822 
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2174 - loss: 2.3429
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2176 - loss: 2.3417
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2172 - loss: 2.3416
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 25ms/step - accuracy: 0.1559 - loss: 2.3534
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 25ms/step - accuracy: 0.1559 - loss: 2.3534[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.2898 - loss: 1.9775[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m425/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 46ms/step - accuracy: 0.1633 - loss: 2.6077
[1m427/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 46ms/step - accuracy: 0.1633 - loss: 2.6076[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m346/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 27ms/step - accuracy: 0.1753 - loss: 2.4474[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2071 - loss: 2.2004
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2071 - loss: 2.2004[32m [repeated 233x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.4156 - loss: 1.6139 
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.4156 - loss: 1.6139
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 46ms/step - accuracy: 0.5457 - loss: 1.2849 - val_accuracy: 0.3767 - val_loss: 1.9253
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m20s[0m 21ms/step - accuracy: 0.1607 - loss: 2.3225[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 311ms/step
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 5/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step  
[1m 9/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m13/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m23/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m27/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m74s[0m 63ms/step - accuracy: 0.1533 - loss: 2.6371 - val_accuracy: 0.1791 - val_loss: 2.2704[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 7/22[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:39[0m 136ms/step - accuracy: 0.1250 - loss: 2.6471[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m35/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m39/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   2/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:23[0m 72ms/step - accuracy: 0.1250 - loss: 2.6142 
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m44/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 79ms/step - accuracy: 0.1389 - loss: 2.5939
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:25[0m 74ms/step - accuracy: 0.1432 - loss: 2.5754
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m390/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 52ms/step - accuracy: 0.3472 - loss: 1.8664
[1m391/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.3472 - loss: 1.8664 [32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m389/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 52ms/step - accuracy: 0.3472 - loss: 1.8664[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:26[0m 75ms/step - accuracy: 0.1471 - loss: 2.5683
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:24[0m 73ms/step - accuracy: 0.1503 - loss: 2.5657
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 14ms/step
[1m62/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 70ms/step - accuracy: 0.1506 - loss: 2.5687
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 68ms/step - accuracy: 0.1513 - loss: 2.5731
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m302/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.1784 - loss: 2.6122 
[1m304/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.1783 - loss: 2.6123
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1530 - loss: 2.5705
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m69/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[1m72/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.1533 - loss: 2.5725
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m76/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[1m79/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1554 - loss: 2.5671
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1570 - loss: 2.5624
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 34ms/step - accuracy: 0.3176 - loss: 1.8391
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 33ms/step - accuracy: 0.3176 - loss: 1.8391
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 33ms/step - accuracy: 0.3176 - loss: 1.8392[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m82/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1588 - loss: 2.5578
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  18/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1602 - loss: 2.5527
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1606 - loss: 2.5523
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1613 - loss: 2.5539
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 19ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1614 - loss: 2.5567
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1614 - loss: 2.5590
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1615 - loss: 2.5602
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1614 - loss: 2.5617
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 61ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1616 - loss: 2.5631
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1615 - loss: 2.5664
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m  6/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step 
[1m  9/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1614 - loss: 2.5693
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 13/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 18/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  33/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1613 - loss: 2.5704
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.1610 - loss: 2.5723 
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 21/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 25/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 29/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 34/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1610 - loss: 2.5738
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1609 - loss: 2.5745
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.3161 - loss: 1.8954
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.3161 - loss: 1.8953[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1608 - loss: 2.5750
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 37/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 40/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 44/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.1606 - loss: 2.5767 
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.3177 - loss: 1.8396[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 48/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 57/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 62/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1604 - loss: 2.5784
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1604 - loss: 2.5790
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1604 - loss: 2.5797
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 66/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 70/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.1604 - loss: 2.5802 
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1605 - loss: 2.5804
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 77/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1606 - loss: 2.5806
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1607 - loss: 2.5807
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 81/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 85/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.1608 - loss: 2.5806 
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 88/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 92/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m 97/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m102/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m391/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 35ms/step - accuracy: 0.1767 - loss: 2.6149
[1m393/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 35ms/step - accuracy: 0.1767 - loss: 2.6150[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m106/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593422)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593422)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m115/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[1m120/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m125/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 14ms/step
[1m131/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m134/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 14ms/step
[1m137/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.1615 - loss: 2.5813
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m556/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 45ms/step - accuracy: 0.1631 - loss: 2.6047[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m142/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 36ms/step - accuracy: 0.1701 - loss: 2.4316  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 34ms/step - accuracy: 0.1852 - loss: 2.4540
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m147/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 14ms/step
[1m152/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1615 - loss: 2.5816
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1615 - loss: 2.5820
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m157/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 14ms/step
[1m162/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1615 - loss: 2.5824
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1614 - loss: 2.5828
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 32ms/step - accuracy: 0.2079 - loss: 2.2002
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 32ms/step - accuracy: 0.2080 - loss: 2.2002[32m [repeated 160x across cluster][0m
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m166/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1614 - loss: 2.5833
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1613 - loss: 2.5838
[36m(train_cnn_ray_tune pid=1593422)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1612 - loss: 2.5842
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1611 - loss: 2.5846

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:12:24. Total running time: 7min 44s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             461.048 │
│ time_total_s                 461.048 │
│ training_iteration                 1 │
│ val_accuracy                 0.37669 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:12:24. Total running time: 7min 44s
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1609 - loss: 2.5856
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1609 - loss: 2.5860
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1608 - loss: 2.5863
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1608 - loss: 2.5866
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.3178 - loss: 1.8398
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.3178 - loss: 1.8398
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.3178 - loss: 1.8398
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1607 - loss: 2.5872
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 32ms/step - accuracy: 0.2081 - loss: 2.2001[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1607 - loss: 2.5876
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1606 - loss: 2.5883
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.1606 - loss: 2.5890
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 55ms/step - accuracy: 0.1607 - loss: 2.5895 
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.1777 - loss: 2.4595 
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.1777 - loss: 2.4595
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 27ms/step - accuracy: 0.1562 - loss: 2.3526 - val_accuracy: 0.1811 - val_loss: 2.1934
[36m(train_cnn_ray_tune pid=1593431)[0m Epoch 14/18
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:36[0m 134ms/step - accuracy: 0.1250 - loss: 2.3589
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 30ms/step - accuracy: 0.1763 - loss: 2.4466 - val_accuracy: 0.1837 - val_loss: 2.3000
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 24/29
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 78ms/step - accuracy: 0.1562 - loss: 2.4892
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 26ms/step - accuracy: 0.1719 - loss: 2.3738
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.1777 - loss: 2.4593
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.1777 - loss: 2.4593[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 33ms/step - accuracy: 0.3178 - loss: 1.8400
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 33ms/step - accuracy: 0.3178 - loss: 1.8400
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 33ms/step - accuracy: 0.3178 - loss: 1.8400
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 25ms/step - accuracy: 0.1752 - loss: 2.3594
[1m  9/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 25ms/step - accuracy: 0.1782 - loss: 2.3529
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.2085 - loss: 2.1998[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 12/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.1819 - loss: 2.3490
[1m 15/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.1839 - loss: 2.3479
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 18/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.1838 - loss: 2.3499
[1m 20/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.1841 - loss: 2.3510
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 22/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.1844 - loss: 2.3524
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 25/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.1844 - loss: 2.3556
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 28/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.1844 - loss: 2.3588
[1m 30/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.1846 - loss: 2.3602
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m548/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 52ms/step - accuracy: 0.2367 - loss: 2.2602
[1m549/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 52ms/step - accuracy: 0.2367 - loss: 2.2602
[1m550/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 52ms/step - accuracy: 0.2367 - loss: 2.2602
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 33/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.1847 - loss: 2.3625
[1m 36/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.1850 - loss: 2.3648
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 38/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.1851 - loss: 2.3662
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 40/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.1853 - loss: 2.3675
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 33ms/step - accuracy: 0.3178 - loss: 1.8401
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 33ms/step - accuracy: 0.3178 - loss: 1.8401
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 33ms/step - accuracy: 0.3178 - loss: 1.8401
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 43/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.1854 - loss: 2.3691
[1m 45/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.1856 - loss: 2.3701
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m547/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 51ms/step - accuracy: 0.3478 - loss: 1.8655
[1m549/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 51ms/step - accuracy: 0.3478 - loss: 1.8655[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 47/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 24ms/step - accuracy: 0.1857 - loss: 2.3711
[1m 49/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.1859 - loss: 2.3718
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.1861 - loss: 2.3723
[1m 53/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.1863 - loss: 2.3728
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 46ms/step - accuracy: 0.1875 - loss: 2.3718 
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 50ms/step - accuracy: 0.1836 - loss: 2.3784
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 62/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.1869 - loss: 2.3759
[1m 64/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.1870 - loss: 2.3767
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m558/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 51ms/step - accuracy: 0.3478 - loss: 1.8654[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 173/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 50ms/step - accuracy: 0.1568 - loss: 2.6056
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 50ms/step - accuracy: 0.1567 - loss: 2.6059[32m [repeated 152x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.2900 - loss: 1.9763 - val_accuracy: 0.3290 - val_loss: 1.8210
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.2812 - loss: 2.2318 
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 22ms/step - accuracy: 0.1672 - loss: 2.3540[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m170/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.1837 - loss: 2.4033 
[1m173/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.1835 - loss: 2.4038
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.1626 - loss: 2.3402 
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.1626 - loss: 2.3402
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 58ms/step - accuracy: 0.2041 - loss: 2.3424 - val_accuracy: 0.2211 - val_loss: 2.0865[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m Epoch 10/21[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 79ms/step - accuracy: 0.3750 - loss: 2.0103[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m102/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.1621 - loss: 2.5629[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 31ms/step - accuracy: 0.2091 - loss: 2.1987
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 31ms/step - accuracy: 0.2091 - loss: 2.1987[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 87ms/step - accuracy: 0.1875 - loss: 2.4970
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 31ms/step - accuracy: 0.1510 - loss: 2.6437
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m104/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.1622 - loss: 2.5629
[1m106/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.1623 - loss: 2.5629[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 31ms/step - accuracy: 0.2091 - loss: 2.1986[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 28ms/step - accuracy: 0.2892 - loss: 1.9581
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 28ms/step - accuracy: 0.2892 - loss: 1.9576
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 28ms/step - accuracy: 0.2893 - loss: 1.9571
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m260/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.1805 - loss: 2.4153
[1m262/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.1804 - loss: 2.4155[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m247/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.1809 - loss: 2.4139[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.4826 - loss: 1.4352  
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 30ms/step - accuracy: 0.4677 - loss: 1.4770
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 29ms/step - accuracy: 0.2902 - loss: 1.9513
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 29ms/step - accuracy: 0.2903 - loss: 1.9510[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 415ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 3/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 28ms/step  
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 36ms/step - accuracy: 0.4169 - loss: 1.6096 - val_accuracy: 0.3954 - val_loss: 1.6620[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 6/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 9/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[1m11/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 25ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[1m17/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m19/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.3391 - loss: 1.7041[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m22/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[1m24/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m28/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m34/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step
[1m36/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m39/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 22ms/step
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m43/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 23ms/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 23ms/step
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 22ms/step
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 22ms/step
[1m64/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 22ms/step
[1m76/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m79/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 22ms/step
[1m82/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m85/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 26ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 26ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 46ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m  3/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 26ms/step
[1m  6/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m  9/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step
[1m 11/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 15/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step
[1m 18/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 58ms/step - accuracy: 0.3479 - loss: 1.8653 - val_accuracy: 0.2531 - val_loss: 2.1652[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m Epoch 10/22[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:08[0m 110ms/step - accuracy: 0.5000 - loss: 1.4631[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 21/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 20ms/step
[1m 24/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 92/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 45ms/step - accuracy: 0.2458 - loss: 2.1888[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 21ms/step - accuracy: 0.1629 - loss: 2.3380
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 21ms/step - accuracy: 0.1629 - loss: 2.3380[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 82ms/step - accuracy: 0.1875 - loss: 1.8513
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3242 - loss: 1.7101 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 28/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 31/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m238/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 38ms/step - accuracy: 0.1643 - loss: 2.5633
[1m239/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 38ms/step - accuracy: 0.1643 - loss: 2.5633[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 35/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 38/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 21ms/step - accuracy: 0.1860 - loss: 2.3672[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 41/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 44/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 47/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[1m 50/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[1m 56/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 59/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 62/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.1651 - loss: 2.3400
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.1651 - loss: 2.3399
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.1651 - loss: 2.3398
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 65/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 69/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 71/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 20ms/step
[1m 74/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 76/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 79/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m471/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 24ms/step - accuracy: 0.1771 - loss: 2.4271
[1m474/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 24ms/step - accuracy: 0.1770 - loss: 2.4272[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 82/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 20ms/step
[1m 85/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 88/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 20ms/step
[1m 92/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m 95/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 20ms/step
[1m 98/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m468/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 24ms/step - accuracy: 0.1771 - loss: 2.4270[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m101/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m104/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 20ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m106/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 21ms/step
[1m109/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593444)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m112/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 21ms/step
[1m115/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 29ms/step - accuracy: 0.3436 - loss: 1.7709
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 29ms/step - accuracy: 0.3434 - loss: 1.7712[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m117/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 21ms/step
[1m119/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 21ms/step - accuracy: 0.1632 - loss: 2.3374
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 21ms/step - accuracy: 0.1632 - loss: 2.3374
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 21ms/step - accuracy: 0.1632 - loss: 2.3374
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m122/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 21ms/step
[1m125/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m127/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 35ms/step - accuracy: 0.2094 - loss: 2.1981 - val_accuracy: 0.2834 - val_loss: 2.0359[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m130/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m133/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m136/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m140/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 21ms/step
[1m143/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m146/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m33s[0m 46ms/step - accuracy: 0.1555 - loss: 2.6070[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m149/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 21ms/step
[1m151/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m154/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 21ms/step
[1m158/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m161/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m164/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=1593444)[0m 
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 21ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:12:40. Total running time: 8min 0s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             477.259 │
│ time_total_s                 477.259 │
│ training_iteration                 1 │
│ val_accuracy                  0.2531 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:12:40. Total running time: 8min 0s

Trial status: 16 RUNNING | 4 TERMINATED
Current time: 2025-10-31 15:12:41. Total running time: 8min 0s
Logical resource usage: 16.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24                                              │
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25                                              │
│ trial_8b084    RUNNING              2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 16                  3                 1          0.000172735         21                                              │
│ trial_8b084    RUNNING              3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 64                  3                 0          0.000176203         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27                                              │
│ trial_8b084    RUNNING              2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15                                              │
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17                                              │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593442)[0m Epoch 9/22[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m211/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 44ms/step - accuracy: 0.2427 - loss: 2.2044[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 20ms/step - accuracy: 0.1654 - loss: 2.3350
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 20ms/step - accuracy: 0.1654 - loss: 2.3350[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:15[0m 116ms/step - accuracy: 0.3750 - loss: 1.8506
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.3715 - loss: 1.7429  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m213/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 44ms/step - accuracy: 0.2426 - loss: 2.2045
[1m215/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 43ms/step - accuracy: 0.2426 - loss: 2.2046[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 20ms/step - accuracy: 0.1653 - loss: 2.3352[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 27ms/step - accuracy: 0.1763 - loss: 2.4294 - val_accuracy: 0.1854 - val_loss: 2.2870
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:33[0m 80ms/step - accuracy: 0.1875 - loss: 2.3050
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 26ms/step - accuracy: 0.1528 - loss: 2.4335 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1470 - loss: 2.4446
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m355/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1993 - loss: 2.3144
[1m357/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1994 - loss: 2.3144[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m365/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1995 - loss: 2.3142[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 28ms/step - accuracy: 0.3222 - loss: 1.8483
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 28ms/step - accuracy: 0.3222 - loss: 1.8483
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 28ms/step - accuracy: 0.3222 - loss: 1.8483
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 28ms/step - accuracy: 0.3392 - loss: 1.7803
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 28ms/step - accuracy: 0.3391 - loss: 1.7803[32m [repeated 192x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 24ms/step - accuracy: 0.1633 - loss: 2.3370 - val_accuracy: 0.2044 - val_loss: 2.1731[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 34ms/step - accuracy: 0.4145 - loss: 1.5941[32m [repeated 160x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m Epoch 15/15[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m334/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.2425 - loss: 2.2110[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.1654 - loss: 2.3329
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.1654 - loss: 2.3329[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 95ms/step - accuracy: 0.2500 - loss: 2.3369
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.2500 - loss: 2.3309
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m336/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.2425 - loss: 2.2111
[1m338/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.2425 - loss: 2.2112[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.1654 - loss: 2.3329[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m348/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.2425 - loss: 2.2116 
[1m350/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.2425 - loss: 2.2117
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42[0m 88ms/step - accuracy: 0.3125 - loss: 2.1187
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 15ms/step - accuracy: 0.1810 - loss: 2.4400 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 17ms/step - accuracy: 0.1660 - loss: 2.4213
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m231/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 23ms/step - accuracy: 0.1786 - loss: 2.4296
[1m234/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 23ms/step - accuracy: 0.1785 - loss: 2.4295[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m528/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 32ms/step - accuracy: 0.1685 - loss: 2.6163[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 28ms/step - accuracy: 0.3369 - loss: 1.7849
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 28ms/step - accuracy: 0.3369 - loss: 1.7849[32m [repeated 269x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m21s[0m 44ms/step - accuracy: 0.1562 - loss: 2.6050[32m [repeated 179x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.3247 - loss: 1.8462
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.3247 - loss: 1.8461
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.3248 - loss: 1.8461
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 23ms/step - accuracy: 0.1654 - loss: 2.3328 - val_accuracy: 0.1950 - val_loss: 2.1776
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 64ms/step - accuracy: 0.0625 - loss: 2.5192
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 17ms/step - accuracy: 0.0898 - loss: 2.3764 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.1163 - loss: 2.3161
[36m(train_cnn_ray_tune pid=1593431)[0m Epoch 15/18
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m346/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.2425 - loss: 2.2115[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m342/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.2425 - loss: 2.2113
[1m344/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.2425 - loss: 2.2114
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 36ms/step - accuracy: 0.1688 - loss: 2.6158 - val_accuracy: 0.1808 - val_loss: 2.3751
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 19/24
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2965 - loss: 1.9359 
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2966 - loss: 1.9359
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2966 - loss: 1.9359
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2966 - loss: 1.9358
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 10/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.1943 - loss: 2.5254
[1m 12/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.1873 - loss: 2.5331
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2966 - loss: 1.9358
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2966 - loss: 1.9358
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.2118 - loss: 2.4205  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.1996 - loss: 2.4789
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m492/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 42ms/step - accuracy: 0.2431 - loss: 2.2138
[1m494/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 42ms/step - accuracy: 0.2431 - loss: 2.2138[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 14/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.1824 - loss: 2.5382
[1m 16/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.1793 - loss: 2.5422
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2966 - loss: 1.9358
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2966 - loss: 1.9358
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2966 - loss: 1.9357
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2966 - loss: 1.9357
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2966 - loss: 1.9357
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2966 - loss: 1.9357
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m498/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 42ms/step - accuracy: 0.2431 - loss: 2.2139[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9357
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9356
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9356
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9356
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.3367 - loss: 1.7848
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.3367 - loss: 1.7848[32m [repeated 294x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9356
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9355
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9355
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9355
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9355
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9355
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9355
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9354
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9354
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9354
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9354
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9354
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m18s[0m 19ms/step - accuracy: 0.1625 - loss: 2.3025[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2967 - loss: 1.9354
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2968 - loss: 1.9354
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.2968 - loss: 1.9353
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.2968 - loss: 1.9353
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.2968 - loss: 1.9353
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.1834 - loss: 2.4451
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.1834 - loss: 2.4451
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.1834 - loss: 2.4451[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.2968 - loss: 1.9353
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.2968 - loss: 1.9353
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 106ms/step - accuracy: 0.2500 - loss: 2.1937[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.3275 - loss: 1.8420
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.3275 - loss: 1.8420
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 27ms/step - accuracy: 0.3275 - loss: 1.8419
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 37/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 39ms/step - accuracy: 0.1919 - loss: 2.2893[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 26ms/step - accuracy: 0.1747 - loss: 2.4287 - val_accuracy: 0.1800 - val_loss: 2.2853[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 26/29[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.3368 - loss: 1.7844 
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.3368 - loss: 1.7844[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.3369 - loss: 1.7843
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.3369 - loss: 1.7843[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m141/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.1602 - loss: 2.5680
[1m143/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.1601 - loss: 2.5681[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 41ms/step - accuracy: 0.1597 - loss: 2.3302  
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.1549 - loss: 2.3620
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m582/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.2438 - loss: 2.2140
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 41ms/step - accuracy: 0.2438 - loss: 2.2140[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m577/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.2438 - loss: 2.2140[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 33ms/step - accuracy: 0.4168 - loss: 1.6081
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 33ms/step - accuracy: 0.4168 - loss: 1.6081[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m234/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.1737 - loss: 2.5891 
[1m236/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.1737 - loss: 2.5892
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 19ms/step - accuracy: 0.1625 - loss: 2.3158[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 42ms/step - accuracy: 0.1568 - loss: 2.6043[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 28ms/step - accuracy: 0.3368 - loss: 1.7845
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 28ms/step - accuracy: 0.3368 - loss: 1.7845
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 28ms/step - accuracy: 0.3368 - loss: 1.7845[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 104ms/step - accuracy: 0.4375 - loss: 1.9494
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 38ms/step - accuracy: 0.3351 - loss: 2.0673  
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 111ms/step - accuracy: 0.1562 - loss: 2.2577
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.3368 - loss: 1.7844
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.3368 - loss: 1.7844
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.3368 - loss: 1.7844
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m175/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 38ms/step - accuracy: 0.2035 - loss: 2.2937[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 47ms/step - accuracy: 0.2438 - loss: 2.2140 - val_accuracy: 0.2294 - val_loss: 2.1907
[36m(train_cnn_ray_tune pid=1593428)[0m Epoch 14/20
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.3373 - loss: 1.7834
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.3373 - loss: 1.7834[32m [repeated 232x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53:38[0m 6s/step - accuracy: 0.2188 - loss: 2.2160
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 73/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 39ms/step - accuracy: 0.2452 - loss: 2.1915
[1m 75/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 39ms/step - accuracy: 0.2451 - loss: 2.1915[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m355/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 29ms/step - accuracy: 0.1746 - loss: 2.5858
[1m357/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 29ms/step - accuracy: 0.1747 - loss: 2.5858[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m359/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 29ms/step - accuracy: 0.1747 - loss: 2.5858[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.4167 - loss: 1.6100
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.4167 - loss: 1.6100[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 24ms/step - accuracy: 0.1827 - loss: 2.4412
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 24ms/step - accuracy: 0.1827 - loss: 2.4412
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 24ms/step - accuracy: 0.1827 - loss: 2.4412
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m306/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1608 - loss: 2.5607 
[1m308/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1609 - loss: 2.5606
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.4167 - loss: 1.6102[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 19ms/step - accuracy: 0.1637 - loss: 2.3164[32m [repeated 164x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 32ms/step - accuracy: 0.2979 - loss: 1.9329 - val_accuracy: 0.3452 - val_loss: 1.8190
[36m(train_cnn_ray_tune pid=1593436)[0m Epoch 11/21
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.3021 - loss: 1.7316 
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m178/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m15s[0m 39ms/step - accuracy: 0.2461 - loss: 2.1922[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.1250 - loss: 2.4618
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 14ms/step - accuracy: 0.1975 - loss: 2.3372 
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 19ms/step - accuracy: 0.1639 - loss: 2.3160
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 19ms/step - accuracy: 0.1639 - loss: 2.3160[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 64ms/step - accuracy: 0.2500 - loss: 1.9688[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m204/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 39ms/step - accuracy: 0.2463 - loss: 2.1917
[1m206/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 38ms/step - accuracy: 0.2464 - loss: 2.1916[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m252/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.1834 - loss: 2.4096
[1m255/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.1834 - loss: 2.4096[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 19ms/step - accuracy: 0.4062 - loss: 1.3513 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.4060 - loss: 1.3933
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 325ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m349/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.2066 - loss: 2.2945[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 7/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step   
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m20/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m26/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3076 - loss: 1.8448
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3104 - loss: 1.8414[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m33/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m39/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m80/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 16ms/step - accuracy: 0.2127 - loss: 2.3153[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 37ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.4160 - loss: 1.6134[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m  9/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step 
[1m 15/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 22/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[1m 27/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 34/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[1m 41/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
Trial status: 16 RUNNING | 4 TERMINATED
Current time: 2025-10-31 15:13:11. Total running time: 8min 30s
Logical resource usage: 16.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24                                              │
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25                                              │
│ trial_8b084    RUNNING              2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 16                  3                 1          0.000172735         21                                              │
│ trial_8b084    RUNNING              3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 64                  3                 0          0.000176203         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27                                              │
│ trial_8b084    RUNNING              2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15                                              │
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17                                              │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 47/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 54/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593429)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 60/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 66/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 72/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 78/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 84/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m 90/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 97/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m105/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step
[1m111/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m118/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[1m124/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m129/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m136/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[1m143/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m150/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step
[1m157/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593429)[0m 
[1m163/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:13:12. Total running time: 8min 31s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             508.648 │
│ time_total_s                 508.648 │
│ training_iteration                 1 │
│ val_accuracy                 0.20999 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:13:12. Total running time: 8min 31s
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 32ms/step - accuracy: 0.1754 - loss: 2.5843 - val_accuracy: 0.1806 - val_loss: 2.3679
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 31ms/step - accuracy: 0.3373 - loss: 1.7832 - val_accuracy: 0.2553 - val_loss: 2.1667[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 20/24[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3333 - loss: 1.9730 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 15/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1963 - loss: 2.5371[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 75ms/step - accuracy: 0.1875 - loss: 2.4515
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1997 - loss: 2.5175
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 32ms/step - accuracy: 0.4157 - loss: 1.6150
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 32ms/step - accuracy: 0.4157 - loss: 1.6150[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 71ms/step - accuracy: 0.3125 - loss: 1.7002[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 61/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.1843 - loss: 2.5565
[1m 63/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.1840 - loss: 2.5570[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m519/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 20ms/step - accuracy: 0.1809 - loss: 2.4113
[1m522/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 20ms/step - accuracy: 0.1809 - loss: 2.4113[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 17ms/step - accuracy: 0.1380 - loss: 2.5976 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1490 - loss: 2.5642
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.2474 - loss: 2.1905[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 172/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 23ms/step - accuracy: 0.3555 - loss: 1.7567
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 23ms/step - accuracy: 0.3554 - loss: 1.7564[32m [repeated 191x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m20s[0m 23ms/step - accuracy: 0.4320 - loss: 1.5169[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 32ms/step - accuracy: 0.4156 - loss: 1.6154[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 17ms/step - accuracy: 0.0664 - loss: 2.1708 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 18ms/step - accuracy: 0.0804 - loss: 2.1898
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 22ms/step - accuracy: 0.3412 - loss: 1.7782
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 22ms/step - accuracy: 0.3412 - loss: 1.7782
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 22ms/step - accuracy: 0.3412 - loss: 1.7782
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 22ms/step - accuracy: 0.3414 - loss: 1.7781
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 23ms/step - accuracy: 0.3414 - loss: 1.7781
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 23ms/step - accuracy: 0.3414 - loss: 1.7781
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.1634 - loss: 2.5497 - val_accuracy: 0.1713 - val_loss: 2.3323
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 23ms/step - accuracy: 0.1803 - loss: 2.4123 - val_accuracy: 0.1878 - val_loss: 2.2774
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 21ms/step - accuracy: 0.1641 - loss: 2.3155 - val_accuracy: 0.1932 - val_loss: 2.1745[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 27/29[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 71ms/step - accuracy: 0.2188 - loss: 2.4966
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 20ms/step - accuracy: 0.2161 - loss: 2.4150
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.1701 - loss: 2.7589 
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 35ms/step - accuracy: 0.1558 - loss: 2.5924[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.1961 - loss: 2.3312 
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.1961 - loss: 2.3312
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m224/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.1750 - loss: 2.5782 
[1m226/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.1750 - loss: 2.5783
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.1959 - loss: 2.3314
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 17ms/step - accuracy: 0.1958 - loss: 2.3314[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 86ms/step - accuracy: 0.0625 - loss: 2.9694[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 73/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.1882 - loss: 2.4091
[1m 76/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.1874 - loss: 2.4100[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m500/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 37ms/step - accuracy: 0.2480 - loss: 2.1907
[1m502/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 37ms/step - accuracy: 0.2480 - loss: 2.1907[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m506/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 37ms/step - accuracy: 0.2480 - loss: 2.1907[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 24ms/step - accuracy: 0.3567 - loss: 1.7396
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 24ms/step - accuracy: 0.3567 - loss: 1.7395[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 37ms/step - accuracy: 0.1588 - loss: 2.5987[32m [repeated 127x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2201 - loss: 2.2409    
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2241 - loss: 2.2187
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 17ms/step - accuracy: 0.1951 - loss: 2.3323[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 18ms/step - accuracy: 0.1719 - loss: 2.2515
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 18ms/step - accuracy: 0.1723 - loss: 2.2521
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 18ms/step - accuracy: 0.1726 - loss: 2.2528[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 42ms/step - accuracy: 0.2069 - loss: 2.2950 - val_accuracy: 0.2294 - val_loss: 2.0628
[36m(train_cnn_ray_tune pid=1593434)[0m Epoch 14/21
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m196/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.1621 - loss: 2.5473[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 37ms/step - accuracy: 0.4157 - loss: 1.6157 - val_accuracy: 0.3793 - val_loss: 1.7344
[36m(train_cnn_ray_tune pid=1593442)[0m Epoch 10/22
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.4931 - loss: 1.4405 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.4765 - loss: 1.4828
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 99/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.1825 - loss: 2.4155 
[1m102/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.1821 - loss: 2.4159
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 17ms/step - accuracy: 0.1945 - loss: 2.3331
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 17ms/step - accuracy: 0.1945 - loss: 2.3331[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:27[0m 75ms/step - accuracy: 0.4375 - loss: 1.4985[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 81/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 39ms/step - accuracy: 0.2075 - loss: 2.2243
[1m 83/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 39ms/step - accuracy: 0.2077 - loss: 2.2245[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m420/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.1733 - loss: 2.5862
[1m422/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.1733 - loss: 2.5862[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m435/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 28ms/step - accuracy: 0.1734 - loss: 2.5863[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 27ms/step - accuracy: 0.2313 - loss: 2.1590
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 27ms/step - accuracy: 0.2312 - loss: 2.1593[32m [repeated 243x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.3465 - loss: 1.7716[32m [repeated 162x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.1942 - loss: 2.3333
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.1942 - loss: 2.3334
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.1942 - loss: 2.3334
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.1943 - loss: 2.3333[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 18ms/step - accuracy: 0.1703 - loss: 2.2871
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 18ms/step - accuracy: 0.1703 - loss: 2.2872
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 18ms/step - accuracy: 0.1703 - loss: 2.2873[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.2487 - loss: 2.1904 - val_accuracy: 0.2305 - val_loss: 2.1889
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 103ms/step - accuracy: 0.2812 - loss: 2.1381
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2743 - loss: 2.1799  
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 23ms/step - accuracy: 0.1772 - loss: 2.4451 
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 23ms/step - accuracy: 0.1772 - loss: 2.4451
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 42ms/step - accuracy: 0.2554 - loss: 2.1660[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m Epoch 15/20
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 23ms/step - accuracy: 0.1775 - loss: 2.4431
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.1775 - loss: 2.4430[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m207/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m15s[0m 40ms/step - accuracy: 0.2093 - loss: 2.2389
[1m209/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m15s[0m 40ms/step - accuracy: 0.2093 - loss: 2.2391[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m542/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 22ms/step - accuracy: 0.1742 - loss: 2.4134
[1m545/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 22ms/step - accuracy: 0.1742 - loss: 2.4133[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.1641 - loss: 2.5372[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.3589 - loss: 1.7297
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.3589 - loss: 1.7297[32m [repeated 200x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.3589 - loss: 1.7295[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.4420 - loss: 1.5053[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m32s[0m 38ms/step - accuracy: 0.1604 - loss: 2.5759
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m32s[0m 38ms/step - accuracy: 0.1604 - loss: 2.5758
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m32s[0m 38ms/step - accuracy: 0.1604 - loss: 2.5757
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.3590 - loss: 1.7293 
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.3590 - loss: 1.7293[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 33ms/step - accuracy: 0.1740 - loss: 2.5865 - val_accuracy: 0.1793 - val_loss: 2.3613
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 21/24
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.3590 - loss: 1.7287
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.3590 - loss: 1.7287
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.3590 - loss: 1.7286
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 76ms/step - accuracy: 0.2500 - loss: 2.1809
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.3591 - loss: 1.7285
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.3591 - loss: 1.7284
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 26ms/step - accuracy: 0.3591 - loss: 1.7284
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 21ms/step - accuracy: 0.1936 - loss: 2.3340 - val_accuracy: 0.2118 - val_loss: 2.1968
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2852 - loss: 2.1109 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2385 - loss: 2.2074
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m178/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m16s[0m 41ms/step - accuracy: 0.2621 - loss: 2.1717[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.3591 - loss: 1.7277
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.3591 - loss: 1.7277[32m [repeated 190x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 42/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.1969 - loss: 2.4832
[1m 44/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.1964 - loss: 2.4845[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m501/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 36ms/step - accuracy: 0.1646 - loss: 2.5356
[1m503/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 36ms/step - accuracy: 0.1646 - loss: 2.5356[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m509/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 36ms/step - accuracy: 0.1646 - loss: 2.5355[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m27s[0m 34ms/step - accuracy: 0.4301 - loss: 1.5503
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m27s[0m 34ms/step - accuracy: 0.4301 - loss: 1.5503[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 27ms/step - accuracy: 0.2272 - loss: 2.1673[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 23ms/step - accuracy: 0.1789 - loss: 2.4376[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 25ms/step - accuracy: 0.1742 - loss: 2.4129 - val_accuracy: 0.1808 - val_loss: 2.2754
[36m(train_cnn_ray_tune pid=1593421)[0m Epoch 17/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.3592 - loss: 1.7269
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.3592 - loss: 1.7269
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.3592 - loss: 1.7269[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 70ms/step - accuracy: 0.3125 - loss: 2.0263[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m299/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 41ms/step - accuracy: 0.2622 - loss: 2.1748[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 26ms/step - accuracy: 0.3592 - loss: 1.7258
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 26ms/step - accuracy: 0.3592 - loss: 1.7258[32m [repeated 176x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m323/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 41ms/step - accuracy: 0.2621 - loss: 2.1748
[1m325/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 41ms/step - accuracy: 0.2620 - loss: 2.1748[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 40ms/step - accuracy: 0.2126 - loss: 2.2463
[1m466/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 40ms/step - accuracy: 0.2126 - loss: 2.2463[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m472/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 40ms/step - accuracy: 0.2127 - loss: 2.2464[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 27ms/step - accuracy: 0.2272 - loss: 2.1674
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 27ms/step - accuracy: 0.2272 - loss: 2.1674[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.1648 - loss: 2.5349 - val_accuracy: 0.1734 - val_loss: 2.3130
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 86ms/step - accuracy: 0.1562 - loss: 2.3210
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.1597 - loss: 2.3769
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 19ms/step - accuracy: 0.1839 - loss: 2.3343[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m256/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1845 - loss: 2.5468 
[1m258/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1845 - loss: 2.5469
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.3593 - loss: 1.7251[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 22ms/step - accuracy: 0.1700 - loss: 2.2954 - val_accuracy: 0.1972 - val_loss: 2.1618

Trial status: 15 RUNNING | 5 TERMINATED
Current time: 2025-10-31 15:13:41. Total running time: 9min 0s
Logical resource usage: 15.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24                                              │
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25                                              │
│ trial_8b084    RUNNING              2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 16                  3                 1          0.000172735         21                                              │
│ trial_8b084    RUNNING              3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 64                  3                 0          0.000176203         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27                                              │
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17                                              │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15        1            508.648         0.209991 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593431)[0m Epoch 17/18[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:34[0m 81ms/step - accuracy: 0.1250 - loss: 1.7391
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.2569 - loss: 1.5837 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3069 - loss: 1.5824
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.5482 - loss: 1.2894 
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 85/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 34ms/step - accuracy: 0.1873 - loss: 2.4630[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.2271 - loss: 2.1670
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.2271 - loss: 2.1670[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m109/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.1852 - loss: 2.4654
[1m111/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.1850 - loss: 2.4656[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m384/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1841 - loss: 2.5529
[1m386/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1841 - loss: 2.5530
[1m388/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1842 - loss: 2.5530
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m547/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 22ms/step - accuracy: 0.1741 - loss: 2.4000
[1m550/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 22ms/step - accuracy: 0.1742 - loss: 2.4000[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m469/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 40ms/step - accuracy: 0.2612 - loss: 2.1740[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 33ms/step - accuracy: 0.4302 - loss: 1.5553
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 33ms/step - accuracy: 0.4302 - loss: 1.5553[32m [repeated 173x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.1870 - loss: 2.3278 
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.1870 - loss: 2.3278
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:38[0m 85ms/step - accuracy: 0.3750 - loss: 2.1682
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2839 - loss: 2.1665 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 24ms/step - accuracy: 0.1991 - loss: 2.4036[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.1873 - loss: 2.3273[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.3593 - loss: 1.7249 - val_accuracy: 0.2598 - val_loss: 2.1539[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m  92/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 27ms/step - accuracy: 0.3099 - loss: 1.8995
[1m  94/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 27ms/step - accuracy: 0.3100 - loss: 1.8996
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 27ms/step - accuracy: 0.3101 - loss: 1.8997
[36m(train_cnn_ray_tune pid=1593441)[0m Epoch 12/22[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 45ms/step - accuracy: 0.2137 - loss: 2.2479 - val_accuracy: 0.2359 - val_loss: 2.0527
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.1562 - loss: 2.2637[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3659 - loss: 1.7102 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3460 - loss: 1.7832
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 31/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 40ms/step - accuracy: 0.2107 - loss: 2.2541[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.2267 - loss: 2.1667
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.2267 - loss: 2.1667[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 54/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 41ms/step - accuracy: 0.2111 - loss: 2.2742
[1m 56/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 40ms/step - accuracy: 0.2111 - loss: 2.2749[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m552/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 30ms/step - accuracy: 0.1846 - loss: 2.5552
[1m554/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 30ms/step - accuracy: 0.1846 - loss: 2.5553[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m579/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.2611 - loss: 2.1725[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 28ms/step - accuracy: 0.3707 - loss: 1.6934
[1m 145/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 28ms/step - accuracy: 0.3707 - loss: 1.6931[32m [repeated 233x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1636 - loss: 2.5540 
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1636 - loss: 2.5540
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 79ms/step - accuracy: 0.3750 - loss: 1.6138
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.3299 - loss: 1.7713 
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 28ms/step - accuracy: 0.3701 - loss: 1.6906[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.1636 - loss: 2.5538[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 19ms/step - accuracy: 0.1760 - loss: 2.2835
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 19ms/step - accuracy: 0.1760 - loss: 2.2835
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 19ms/step - accuracy: 0.1760 - loss: 2.2835[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m Epoch 29/29[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 26ms/step - accuracy: 0.1743 - loss: 2.4000 - val_accuracy: 0.1833 - val_loss: 2.2687
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 34ms/step - accuracy: 0.1845 - loss: 2.5557 - val_accuracy: 0.1854 - val_loss: 2.3541
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 88ms/step - accuracy: 0.1562 - loss: 2.7511
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 105ms/step - accuracy: 0.3438 - loss: 1.8808
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.1758 - loss: 2.2841 
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.1758 - loss: 2.2842
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 21/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 32ms/step - accuracy: 0.1863 - loss: 2.5700[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 39ms/step - accuracy: 0.1636 - loss: 2.5530
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 39ms/step - accuracy: 0.1636 - loss: 2.5530[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.1860 - loss: 2.5463
[1m 53/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.1862 - loss: 2.5461[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m328/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 22ms/step - accuracy: 0.1807 - loss: 2.3879
[1m331/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 22ms/step - accuracy: 0.1807 - loss: 2.3879[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m345/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 22ms/step - accuracy: 0.1808 - loss: 2.3880[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 39ms/step - accuracy: 0.1636 - loss: 2.5529
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 28ms/step - accuracy: 0.3654 - loss: 1.6873
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 28ms/step - accuracy: 0.3654 - loss: 1.6872[32m [repeated 190x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 28ms/step - accuracy: 0.3199 - loss: 1.8756[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 39ms/step - accuracy: 0.1636 - loss: 2.5527[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m77s[0m 31ms/step - accuracy: 0.2265 - loss: 2.1661 - val_accuracy: 0.3103 - val_loss: 2.0148
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 26ms/step - accuracy: 0.3760 - loss: 1.7054
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 26ms/step - accuracy: 0.3759 - loss: 1.7055
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 26ms/step - accuracy: 0.3759 - loss: 1.7056[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:41[0m 87ms/step - accuracy: 0.1875 - loss: 1.9988
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2435 - loss: 2.0420 
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 12/23[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 46ms/step - accuracy: 0.2611 - loss: 2.1724 - val_accuracy: 0.2327 - val_loss: 2.1847
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m132/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 41ms/step - accuracy: 0.2691 - loss: 2.1079[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:40[0m 86ms/step - accuracy: 0.1875 - loss: 1.9878
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1758 - loss: 2.2662 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.1637 - loss: 2.5520
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.1637 - loss: 2.5520[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m213/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m11s[0m 31ms/step - accuracy: 0.1866 - loss: 2.5559
[1m215/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m11s[0m 31ms/step - accuracy: 0.1867 - loss: 2.5559[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m532/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 23ms/step - accuracy: 0.1810 - loss: 2.3884
[1m535/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 23ms/step - accuracy: 0.1810 - loss: 2.3884[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m559/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 23ms/step - accuracy: 0.1810 - loss: 2.3882[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 28ms/step - accuracy: 0.3650 - loss: 1.6813
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 28ms/step - accuracy: 0.3651 - loss: 1.6813[32m [repeated 182x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.3199 - loss: 1.8725[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m262/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1867 - loss: 2.5562 
[1m264/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1866 - loss: 2.5562
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 19ms/step - accuracy: 0.1768 - loss: 2.2846[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 22ms/step - accuracy: 0.1902 - loss: 2.3254 - val_accuracy: 0.2096 - val_loss: 2.1972
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 26ms/step - accuracy: 0.3751 - loss: 1.7086
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 26ms/step - accuracy: 0.3751 - loss: 1.7086
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 26ms/step - accuracy: 0.3751 - loss: 1.7087[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m Epoch 18/25
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 26ms/step - accuracy: 0.1811 - loss: 2.3880 - val_accuracy: 0.1774 - val_loss: 2.2621
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 322ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 7/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step   
[1m13/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m24/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m30/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[1m36/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m43/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[1m80/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.4680 - loss: 1.4562 
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.4680 - loss: 1.4562
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m270/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 39ms/step - accuracy: 0.2691 - loss: 2.1157[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 48ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m  7/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step 
[1m 13/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 19/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 23/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m Epoch 19/28
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 29/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 37/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 43/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 80ms/step - accuracy: 0.1562 - loss: 2.6661
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.1615 - loss: 2.5797
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 48/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 54/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 25ms/step - accuracy: 0.3746 - loss: 1.7104
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 25ms/step - accuracy: 0.3746 - loss: 1.7104[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 59/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 65/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 80/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593433)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 87/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 13/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.1653 - loss: 2.5398
[1m 15/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.1653 - loss: 2.5440[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m402/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 29ms/step - accuracy: 0.1861 - loss: 2.5559
[1m404/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 29ms/step - accuracy: 0.1861 - loss: 2.5559[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m 93/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 99/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m105/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step
[1m112/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m118/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step
[1m125/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m131/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.2109 - loss: 2.2776[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m138/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step
[1m145/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m151/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[1m157/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 27ms/step - accuracy: 0.3206 - loss: 1.8701
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 27ms/step - accuracy: 0.3206 - loss: 1.8701[32m [repeated 161x across cluster][0m
[36m(train_cnn_ray_tune pid=1593433)[0m 
[1m163/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 9ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:14:05. Total running time: 9min 25s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             562.331 │
│ time_total_s                 562.331 │
│ training_iteration                 1 │
│ val_accuracy                 0.17743 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:14:05. Total running time: 9min 25s
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.3206 - loss: 1.8697 [32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 21ms/step - accuracy: 0.1767 - loss: 2.2849 - val_accuracy: 0.1980 - val_loss: 2.1515
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42[0m 88ms/step - accuracy: 0.2500 - loss: 2.3184
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 24ms/step - accuracy: 0.1981 - loss: 2.3928[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 37ms/step - accuracy: 0.2535 - loss: 2.1862 
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.3669 - loss: 1.6759
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.3669 - loss: 1.6759
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 26ms/step - accuracy: 0.3669 - loss: 1.6758[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.1748 - loss: 2.4859 - val_accuracy: 0.1795 - val_loss: 2.2944
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 25ms/step - accuracy: 0.4690 - loss: 1.4559
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 25ms/step - accuracy: 0.4690 - loss: 1.4559
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 25ms/step - accuracy: 0.4690 - loss: 1.4559
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.3670 - loss: 1.6757 
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.3670 - loss: 1.6757
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m127/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 34ms/step - accuracy: 0.1771 - loss: 2.4967[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m Epoch 11/22[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:37[0m 84ms/step - accuracy: 0.4375 - loss: 1.1896
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 29ms/step - accuracy: 0.3785 - loss: 1.5241 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.3673 - loss: 1.6749
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.3673 - loss: 1.6748[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m157/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 34ms/step - accuracy: 0.1777 - loss: 2.4930
[1m159/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 34ms/step - accuracy: 0.1777 - loss: 2.4928[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m578/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.1855 - loss: 2.5540
[1m580/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.1855 - loss: 2.5540[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m445/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 38ms/step - accuracy: 0.2707 - loss: 2.1209[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 25ms/step - accuracy: 0.2287 - loss: 2.1226
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 25ms/step - accuracy: 0.2287 - loss: 2.1227[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 25ms/step - accuracy: 0.2288 - loss: 2.1231[32m [repeated 97x across cluster][0m

Trial status: 14 RUNNING | 6 TERMINATED
Current time: 2025-10-31 15:14:11. Total running time: 9min 30s
Logical resource usage: 14.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24                                              │
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25                                              │
│ trial_8b084    RUNNING              2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 16                  3                 1          0.000172735         21                                              │
│ trial_8b084    RUNNING              3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 64                  3                 0          0.000176203         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27                                              │
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17                                              │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29        1            562.331         0.177428 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15        1            508.648         0.209991 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m44s[0m 38ms/step - accuracy: 0.4295 - loss: 1.5584 - val_accuracy: 0.3900 - val_loss: 1.7778[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 25ms/step - accuracy: 0.4694 - loss: 1.4556[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 33ms/step - accuracy: 0.1855 - loss: 2.5540 - val_accuracy: 0.1885 - val_loss: 2.3519
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 26ms/step - accuracy: 0.3676 - loss: 1.6743
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.3676 - loss: 1.6742
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.3676 - loss: 1.6742[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:36[0m 82ms/step - accuracy: 0.1875 - loss: 2.2441
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2031 - loss: 2.2623 
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m285/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1785 - loss: 2.4913 [32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 15/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 82ms/step - accuracy: 0.3125 - loss: 2.0211
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.2899 - loss: 2.1228[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.3211 - loss: 1.8670
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.3211 - loss: 1.8670[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 55/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2403 - loss: 2.2086
[1m 57/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2401 - loss: 2.2088[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m311/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1784 - loss: 2.4914
[1m313/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1784 - loss: 2.4914[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 38ms/step - accuracy: 0.2710 - loss: 2.1227[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m33s[0m 37ms/step - accuracy: 0.1774 - loss: 2.4395
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m33s[0m 37ms/step - accuracy: 0.1774 - loss: 2.4398[32m [repeated 130x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m32s[0m 36ms/step - accuracy: 0.1774 - loss: 2.4418[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 27ms/step - accuracy: 0.1978 - loss: 2.3927 - val_accuracy: 0.1961 - val_loss: 2.2412
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.3684 - loss: 1.6726[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 29ms/step - accuracy: 0.3740 - loss: 1.7117 - val_accuracy: 0.2455 - val_loss: 2.2053
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 335ms/step
[1m 6/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step  
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m11/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m16/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.2114 - loss: 2.2745 - val_accuracy: 0.2450 - val_loss: 2.0434
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m20/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m25/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m30/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m35/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m39/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m43/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m49/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 12ms/step
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 11ms/step
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 12ms/step
[1m80/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.2710 - loss: 2.1227 - val_accuracy: 0.2339 - val_loss: 2.1810
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 17ms/step - accuracy: 0.1932 - loss: 2.3198
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 17ms/step - accuracy: 0.1932 - loss: 2.3198
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 17ms/step - accuracy: 0.1932 - loss: 2.3198
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 50ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m  6/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 11/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.4062 - loss: 1.9034
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 16/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 20/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m20s[0m 22ms/step - accuracy: 0.1898 - loss: 2.3766
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m20s[0m 22ms/step - accuracy: 0.1898 - loss: 2.3766
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m20s[0m 22ms/step - accuracy: 0.1898 - loss: 2.3767
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 25/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 29/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 11/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.3195 - loss: 1.9839[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 34/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 39/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 43/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[1m 46/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 51/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 61/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[1m 65/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 71/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m Epoch 17/20[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 75/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 79/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.6250 - loss: 1.2878
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5573 - loss: 1.2881 
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 84/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 89/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m 94/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m100/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593435)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 25ms/step - accuracy: 0.2291 - loss: 2.1269
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 25ms/step - accuracy: 0.2291 - loss: 2.1270[32m [repeated 89x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 70ms/step - accuracy: 0.3125 - loss: 1.8635
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m105/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 12ms/step
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m198/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 36ms/step - accuracy: 0.2330 - loss: 2.2217
[1m200/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 36ms/step - accuracy: 0.2330 - loss: 2.2218[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.1781 - loss: 2.4892
[1m466/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.1781 - loss: 2.4892[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.3299 - loss: 1.7624 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.3367 - loss: 1.7600
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m115/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[1m119/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m125/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 12ms/step
[1m130/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step
[1m134/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m139/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[1m143/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m148/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 12ms/step
[1m152/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m292/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.1806 - loss: 2.5524[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m155/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step
[1m160/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m165/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 22ms/step - accuracy: 0.1898 - loss: 2.3771
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 22ms/step - accuracy: 0.1898 - loss: 2.3771[32m [repeated 139x across cluster][0m
[36m(train_cnn_ray_tune pid=1593435)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:14:20. Total running time: 9min 40s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             577.082 │
│ time_total_s                 577.082 │
│ training_iteration                 1 │
│ val_accuracy                 0.24551 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:14:20. Total running time: 9min 40s
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 22ms/step - accuracy: 0.1899 - loss: 2.3770[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 22ms/step - accuracy: 0.1899 - loss: 2.3770
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 22ms/step - accuracy: 0.1899 - loss: 2.3770
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 22ms/step - accuracy: 0.1899 - loss: 2.3770
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 25ms/step - accuracy: 0.2292 - loss: 2.1273[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.3684 - loss: 1.6726 - val_accuracy: 0.2625 - val_loss: 2.1536[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 19ms/step - accuracy: 0.2018 - loss: 2.4248 
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m146/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m16s[0m 38ms/step - accuracy: 0.2927 - loss: 2.0909[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m310/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2309 - loss: 2.2230 
[1m312/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2309 - loss: 2.2230
[36m(train_cnn_ray_tune pid=1593421)[0m Epoch 19/25[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.2293 - loss: 2.1279
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.2293 - loss: 2.1279[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 65ms/step - accuracy: 0.1875 - loss: 2.4141[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m172/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 38ms/step - accuracy: 0.2918 - loss: 2.0942
[1m174/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 38ms/step - accuracy: 0.2917 - loss: 2.0944[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m334/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2305 - loss: 2.2235
[1m336/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2304 - loss: 2.2235[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3997 - loss: 1.6037 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.3988 - loss: 1.6381
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m346/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.2303 - loss: 2.2237[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 26ms/step - accuracy: 0.4029 - loss: 1.5978
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 26ms/step - accuracy: 0.4028 - loss: 1.5977[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m24s[0m 27ms/step - accuracy: 0.3370 - loss: 1.7920[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 18ms/step - accuracy: 0.1771 - loss: 2.2711[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 20ms/step - accuracy: 0.1933 - loss: 2.3196 - val_accuracy: 0.2209 - val_loss: 2.1992
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.1781 - loss: 2.4874 - val_accuracy: 0.1848 - val_loss: 2.2759
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 17ms/step - accuracy: 0.1945 - loss: 2.3223
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 17ms/step - accuracy: 0.1946 - loss: 2.3219
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 17ms/step - accuracy: 0.1947 - loss: 2.3216
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m272/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.2869 - loss: 2.1049[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m Epoch 20/28
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.1920 - loss: 2.3765
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.1920 - loss: 2.3765[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 93ms/step - accuracy: 0.1562 - loss: 2.6917
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 28ms/step - accuracy: 0.2293 - loss: 2.1280 - val_accuracy: 0.2775 - val_loss: 1.9903
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 13/23
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 99/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.1710 - loss: 2.4740
[1m101/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.1709 - loss: 2.4740[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m480/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 36ms/step - accuracy: 0.2290 - loss: 2.2254
[1m482/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 36ms/step - accuracy: 0.2290 - loss: 2.2254[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:23[0m 72ms/step - accuracy: 0.4375 - loss: 2.0587
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.3368 - loss: 2.0868 
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m328/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2853 - loss: 2.1069[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 25ms/step - accuracy: 0.3985 - loss: 1.5924
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 25ms/step - accuracy: 0.3984 - loss: 1.5924[32m [repeated 217x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 360ms/step
[1m 6/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step  
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m12/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m22/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m26/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m38/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m44/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 25ms/step - accuracy: 0.2679 - loss: 2.0222[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[1m75/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 22ms/step - accuracy: 0.1924 - loss: 2.3763[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 32ms/step - accuracy: 0.1852 - loss: 2.5358 - val_accuracy: 0.1852 - val_loss: 2.3490
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m81/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 26ms/step - accuracy: 0.3382 - loss: 1.7952
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 26ms/step - accuracy: 0.3382 - loss: 1.7953
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 26ms/step - accuracy: 0.3382 - loss: 1.7954
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 53ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m  8/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step 
[1m 14/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 19/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 24/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 29/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593431)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 34/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 41/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 25ms/step - accuracy: 0.3974 - loss: 1.5925
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 25ms/step - accuracy: 0.3974 - loss: 1.5924
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 25ms/step - accuracy: 0.3974 - loss: 1.5924
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 46/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 58/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 65/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 70/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 76/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 83/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m 89/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 94/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.4388 - loss: 1.5113 
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.4388 - loss: 1.5113
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m101/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m107/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m113/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step
[1m119/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m125/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[1m131/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m137/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step
[1m144/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m150/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m157/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[1m162/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 9ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:14:34. Total running time: 9min 53s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             590.703 │
│ time_total_s                 590.703 │
│ training_iteration                 1 │
│ val_accuracy                 0.20352 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:14:34. Total running time: 9min 53s
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m188/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m12s[0m 33ms/step - accuracy: 0.1708 - loss: 2.4712[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 22ms/step - accuracy: 0.1933 - loss: 2.3761
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 22ms/step - accuracy: 0.1933 - loss: 2.3761[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=1593431)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 21ms/step - accuracy: 0.1770 - loss: 2.2714 - val_accuracy: 0.2035 - val_loss: 2.1353
[36m(train_cnn_ray_tune pid=1593415)[0m Epoch 24/24
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m258/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 32ms/step - accuracy: 0.1712 - loss: 2.4703
[1m260/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 32ms/step - accuracy: 0.1712 - loss: 2.4703[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m450/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 36ms/step - accuracy: 0.2838 - loss: 2.1068
[1m452/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 36ms/step - accuracy: 0.2838 - loss: 2.1068[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 94ms/step - accuracy: 0.0938 - loss: 2.8383
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.1152 - loss: 2.6527
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m458/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 36ms/step - accuracy: 0.2838 - loss: 2.1068[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.3957 - loss: 1.5936
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.3956 - loss: 1.5937[32m [repeated 191x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m205/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1865 - loss: 2.5655 
[1m207/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 26ms/step - accuracy: 0.1866 - loss: 2.5651
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.1744 - loss: 2.4772[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.2283 - loss: 2.2260 - val_accuracy: 0.2494 - val_loss: 2.0275
[36m(train_cnn_ray_tune pid=1593434)[0m Epoch 17/21
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 82ms/step - accuracy: 0.2500 - loss: 2.5271
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 17ms/step - accuracy: 0.1953 - loss: 2.3105[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m  1.5097
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.3948 - loss: 1.5945
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.3948 - loss: 1.5945
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.3948 - loss: 1.5946
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1743 - loss: 2.4787 
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1743 - loss: 2.4787
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 68/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 35ms/step - accuracy: 0.2209 - loss: 2.2806[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.4413 - loss: 1.5093
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.4413 - loss: 1.5093
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.4413 - loss: 1.5093
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.3939 - loss: 1.5956
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.3939 - loss: 1.5956[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m100/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.2226 - loss: 2.2656
[1m102/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.2226 - loss: 2.2651[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m423/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.1727 - loss: 2.4699
[1m425/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.1727 - loss: 2.4699[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m361/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.1901 - loss: 2.5472[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 24ms/step - accuracy: 0.2471 - loss: 2.0834
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 23ms/step - accuracy: 0.2471 - loss: 2.0834[32m [repeated 80x across cluster][0m

Trial status: 12 RUNNING | 8 TERMINATED
Current time: 2025-10-31 15:14:41. Total running time: 10min 0s
Logical resource usage: 12.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24                                              │
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25                                              │
│ trial_8b084    RUNNING              2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 16                  3                 1          0.000172735         21                                              │
│ trial_8b084    RUNNING              3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 64                  3                 0          0.000176203         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27                                              │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29        1            562.331         0.177428 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18        1            590.703         0.203515 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15        1            508.648         0.209991 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17        1            577.082         0.245513 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 23ms/step - accuracy: 0.2469 - loss: 2.0841[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.3400 - loss: 1.8042[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.2824 - loss: 2.1073 - val_accuracy: 0.2398 - val_loss: 2.1835
[36m(train_cnn_ray_tune pid=1593428)[0m Epoch 18/20
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 87ms/step - accuracy: 0.3125 - loss: 1.9556
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 25ms/step - accuracy: 0.1939 - loss: 2.3760 - val_accuracy: 0.1935 - val_loss: 2.2309
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 68ms/step - accuracy: 0.2500 - loss: 2.2147
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2721 - loss: 2.1978 
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m228/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m11s[0m 33ms/step - accuracy: 0.2237 - loss: 2.2451[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 24ms/step - accuracy: 0.3928 - loss: 1.5970
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 24ms/step - accuracy: 0.3928 - loss: 1.5970[32m [repeated 136x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 83/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 33ms/step - accuracy: 0.3041 - loss: 2.0730
[1m 85/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 33ms/step - accuracy: 0.3037 - loss: 2.0731[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m561/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.1907 - loss: 2.5380
[1m563/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.1908 - loss: 2.5380[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m280/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.2239 - loss: 2.2396[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 140/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 20ms/step - accuracy: 0.2155 - loss: 2.3398
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 20ms/step - accuracy: 0.2156 - loss: 2.3398[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2456 - loss: 2.0907[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 25ms/step - accuracy: 0.3408 - loss: 1.8049[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4688 - loss: 1.4509 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4804 - loss: 1.4826
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 35ms/step - accuracy: 0.1738 - loss: 2.4682 - val_accuracy: 0.1848 - val_loss: 2.2621
[36m(train_cnn_ray_tune pid=1593439)[0m Epoch 21/28[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 74ms/step - accuracy: 0.1562 - loss: 2.5899[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m17s[0m 29ms/step - accuracy: 0.1908 - loss: 2.5373 - val_accuracy: 0.1874 - val_loss: 2.3402
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 26ms/step - accuracy: 0.4830 - loss: 1.3984 - val_accuracy: 0.3795 - val_loss: 1.7754[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 328ms/step
[1m 7/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step   
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 64ms/step - accuracy: 0.6250 - loss: 1.4760
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 19ms/step - accuracy: 0.5768 - loss: 1.3461 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m13/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m19/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m25/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m30/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m35/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 10ms/step
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step
[1m72/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m78/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[1m84/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 79/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.1721 - loss: 2.4881[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 48ms/step
[1m  7/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step 
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 13/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 19/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 25/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 31/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 37/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 43/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m239/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 30ms/step - accuracy: 0.2939 - loss: 2.0816
[1m241/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 30ms/step - accuracy: 0.2939 - loss: 2.0815
[1m243/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 30ms/step - accuracy: 0.2938 - loss: 2.0815
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 49/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 61/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 67/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 79/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 85/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 92/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m256/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2936 - loss: 2.0814
[1m258/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2936 - loss: 2.0813
[1m260/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2936 - loss: 2.0813
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 22ms/step - accuracy: 0.2450 - loss: 2.0947
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 22ms/step - accuracy: 0.2450 - loss: 2.0947[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m 98/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m104/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593415)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m120/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.1738 - loss: 2.4831
[1m122/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.1738 - loss: 2.4829[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m443/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.2246 - loss: 2.2302
[1m445/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.2246 - loss: 2.2301[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m116/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m122/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[1m128/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m134/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m139/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m145/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m151/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m157/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m277/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2933 - loss: 2.0810[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m163/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593415)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 9ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:14:50. Total running time: 10min 10s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             607.522 │
│ time_total_s                 607.522 │
│ training_iteration                 1 │
│ val_accuracy                 0.18742 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:14:50. Total running time: 10min 10s
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 18ms/step - accuracy: 0.2109 - loss: 2.3440
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 18ms/step - accuracy: 0.2108 - loss: 2.3441[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 18ms/step - accuracy: 0.5067 - loss: 1.3707[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 369ms/step
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3893 - loss: 1.6520 
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 5/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step  
[1m11/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 22ms/step - accuracy: 0.2449 - loss: 2.0957[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m Epoch 14/21[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:25[0m 73ms/step - accuracy: 0.3125 - loss: 1.5659
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 27ms/step - accuracy: 0.3410 - loss: 1.8051 - val_accuracy: 0.3722 - val_loss: 1.7890[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:36[0m 83ms/step - accuracy: 0.2500 - loss: 2.3792
[1m   3/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.2292 - loss: 2.3239 
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 45ms/step
[1m  6/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 15ms/step[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 11/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 16/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 21/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 26/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 31/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 37/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 43/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 49/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 60/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 64/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 68/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 78/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 83/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 88/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m 93/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m169/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 25ms/step - accuracy: 0.1755 - loss: 2.4798[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 32ms/step - accuracy: 0.1744 - loss: 2.4991
[1m  93/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 32ms/step - accuracy: 0.1743 - loss: 2.4990
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 32ms/step - accuracy: 0.1741 - loss: 2.4989
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m 98/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m103/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 11ms/step
[1m116/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m123/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 11ms/step
[1m128/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m135/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m142/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[1m148/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m153/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[1m158/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m164/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m460/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.2246 - loss: 2.2297
[1m462/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.2246 - loss: 2.2297
[1m464/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 30ms/step - accuracy: 0.2246 - loss: 2.2296

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:14:55. Total running time: 10min 14s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             611.614 │
│ time_total_s                 611.614 │
│ training_iteration                 1 │
│ val_accuracy                 0.25809 │
╰──────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593441)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 10ms/step

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:14:55. Total running time: 10min 14s
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 22ms/step - accuracy: 0.2446 - loss: 2.0974
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 22ms/step - accuracy: 0.2446 - loss: 2.0974[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m184/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 25ms/step - accuracy: 0.1759 - loss: 2.4792
[1m186/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 25ms/step - accuracy: 0.1760 - loss: 2.4791 [32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m426/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.2916 - loss: 2.0797
[1m428/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 30ms/step - accuracy: 0.2916 - loss: 2.0797[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m305/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.1781 - loss: 2.4732[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 19ms/step - accuracy: 0.5024 - loss: 1.3771
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 19ms/step - accuracy: 0.5024 - loss: 1.3771[32m [repeated 155x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 18ms/step - accuracy: 0.2065 - loss: 2.3498
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 18ms/step - accuracy: 0.2064 - loss: 2.3498
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 18ms/step - accuracy: 0.2064 - loss: 2.3499
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 30ms/step - accuracy: 0.1744 - loss: 2.4948
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 30ms/step - accuracy: 0.1744 - loss: 2.4946
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 30ms/step - accuracy: 0.1744 - loss: 2.4944
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 19ms/step - accuracy: 0.5023 - loss: 1.3773[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 35ms/step - accuracy: 0.2247 - loss: 2.2268 - val_accuracy: 0.2566 - val_loss: 2.0169
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 14ms/step - accuracy: 0.2064 - loss: 2.2926[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 82ms/step - accuracy: 0.2500 - loss: 1.9761
[36m(train_cnn_ray_tune pid=1593434)[0m Epoch 18/21
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 18ms/step - accuracy: 0.2057 - loss: 2.3509
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 18ms/step - accuracy: 0.2057 - loss: 2.3510
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 18ms/step - accuracy: 0.2057 - loss: 2.3510
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m427/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 26ms/step - accuracy: 0.1786 - loss: 2.4695
[1m429/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 26ms/step - accuracy: 0.1786 - loss: 2.4695
[1m431/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 26ms/step - accuracy: 0.1786 - loss: 2.4694
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 25ms/step - accuracy: 0.2446 - loss: 2.0975 - val_accuracy: 0.3203 - val_loss: 1.9743
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 14/23
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 77ms/step - accuracy: 0.3750 - loss: 2.2502
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2839 - loss: 2.1830 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 29ms/step - accuracy: 0.1752 - loss: 2.4896
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 29ms/step - accuracy: 0.1752 - loss: 2.4896
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 29ms/step - accuracy: 0.1752 - loss: 2.4896
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 11/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.2520 - loss: 2.1910[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.5017 - loss: 1.3772 
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.5017 - loss: 1.3772
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.2047 - loss: 2.3526
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.2047 - loss: 2.3526[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m119/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.2394 - loss: 2.2137
[1m121/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.2393 - loss: 2.2134[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m498/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 26ms/step - accuracy: 0.1789 - loss: 2.4675
[1m501/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 26ms/step - accuracy: 0.1789 - loss: 2.4675[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 29ms/step - accuracy: 0.1752 - loss: 2.4891
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 29ms/step - accuracy: 0.1752 - loss: 2.4891
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 29ms/step - accuracy: 0.1753 - loss: 2.4890
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m519/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 26ms/step - accuracy: 0.1789 - loss: 2.4670[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 19ms/step - accuracy: 0.2368 - loss: 2.1424
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 19ms/step - accuracy: 0.2366 - loss: 2.1421[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m528/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 26ms/step - accuracy: 0.1790 - loss: 2.4668
[1m530/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 26ms/step - accuracy: 0.1790 - loss: 2.4667
[1m532/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 26ms/step - accuracy: 0.1790 - loss: 2.4667
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 14ms/step - accuracy: 0.2047 - loss: 2.2944
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 14ms/step - accuracy: 0.2047 - loss: 2.2944
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 14ms/step - accuracy: 0.2047 - loss: 2.2944
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 29ms/step - accuracy: 0.1755 - loss: 2.4883
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 29ms/step - accuracy: 0.1755 - loss: 2.4883
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 28ms/step - accuracy: 0.1755 - loss: 2.4883
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m547/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 26ms/step - accuracy: 0.1790 - loss: 2.4663
[1m549/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 26ms/step - accuracy: 0.1790 - loss: 2.4662
[1m551/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 26ms/step - accuracy: 0.1790 - loss: 2.4662
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 28ms/step - accuracy: 0.1755 - loss: 2.4883[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 18ms/step - accuracy: 0.2042 - loss: 2.3533[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 34ms/step - accuracy: 0.2906 - loss: 2.0791 - val_accuracy: 0.2398 - val_loss: 2.1897
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 27/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.2701 - loss: 2.1067
[1m 29/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.2721 - loss: 2.1026
[1m 31/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.2733 - loss: 2.0998
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 28ms/step - accuracy: 0.1759 - loss: 2.4875
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 28ms/step - accuracy: 0.1759 - loss: 2.4875
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 28ms/step - accuracy: 0.1759 - loss: 2.4874
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.2500 - loss: 2.5085
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 14ms/step - accuracy: 0.2421 - loss: 2.4407 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 14ms/step - accuracy: 0.2450 - loss: 2.3770
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 16ms/step - accuracy: 0.2043 - loss: 2.2946 - val_accuracy: 0.2226 - val_loss: 2.1796
[36m(train_cnn_ray_tune pid=1593421)[0m Epoch 21/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 80ms/step - accuracy: 0.1875 - loss: 2.2027
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.1962 - loss: 2.1982
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 69/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 28ms/step - accuracy: 0.2852 - loss: 2.0687[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.4678 - loss: 1.4609
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.4678 - loss: 1.4609[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 25/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1668 - loss: 2.4660
[1m 27/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1678 - loss: 2.4632[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m311/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.2331 - loss: 2.2113
[1m313/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.2331 - loss: 2.2113[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m305/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 27ms/step - accuracy: 0.2332 - loss: 2.2113[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 19ms/step - accuracy: 0.2397 - loss: 2.1119
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 19ms/step - accuracy: 0.2397 - loss: 2.1118[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 19ms/step - accuracy: 0.2400 - loss: 2.1105[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 21ms/step - accuracy: 0.2037 - loss: 2.3539 - val_accuracy: 0.2011 - val_loss: 2.2356
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 24ms/step - accuracy: 0.4674 - loss: 1.4615[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 30ms/step - accuracy: 0.1791 - loss: 2.4654 - val_accuracy: 0.1889 - val_loss: 2.2500
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:24[0m 72ms/step - accuracy: 0.1250 - loss: 2.3981
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1432 - loss: 2.3481 
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 85ms/step - accuracy: 0.1562 - loss: 2.3033
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 17/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.4670 - loss: 1.4624
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.4670 - loss: 1.4624
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 24ms/step - accuracy: 0.4670 - loss: 1.4624
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m234/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 29ms/step - accuracy: 0.2926 - loss: 2.0485[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 21ms/step - accuracy: 0.3598 - loss: 1.7750
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 21ms/step - accuracy: 0.3598 - loss: 1.7750[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m209/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.1856 - loss: 2.4243 
[1m211/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 27ms/step - accuracy: 0.1856 - loss: 2.4243
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m204/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 27ms/step - accuracy: 0.1855 - loss: 2.4243
[1m207/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 27ms/step - accuracy: 0.1855 - loss: 2.4243[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m283/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2921 - loss: 2.0492
[1m285/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 29ms/step - accuracy: 0.2921 - loss: 2.0493[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m503/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 28ms/step - accuracy: 0.2319 - loss: 2.2087[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.1776 - loss: 2.4828
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.1776 - loss: 2.4828[32m [repeated 125x across cluster][0m

Trial status: 10 TERMINATED | 10 RUNNING
Current time: 2025-10-31 15:15:11. Total running time: 10min 30s
Logical resource usage: 10.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25                                              │
│ trial_8b084    RUNNING              2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 16                  3                 1          0.000172735         21                                              │
│ trial_8b084    RUNNING              3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27                                              │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24        1            607.522         0.187419 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29        1            562.331         0.177428 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18        1            590.703         0.203515 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   16                 64                  3                 0          0.000176203         22        1            611.614         0.258094 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15        1            508.648         0.209991 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17        1            577.082         0.245513 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 18ms/step - accuracy: 0.1944 - loss: 2.3284
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 18ms/step - accuracy: 0.1946 - loss: 2.3284
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 18ms/step - accuracy: 0.1948 - loss: 2.3283
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.1777 - loss: 2.4825[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 24ms/step - accuracy: 0.4665 - loss: 1.4634[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 22ms/step - accuracy: 0.5011 - loss: 1.3738 - val_accuracy: 0.3724 - val_loss: 1.8059
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 357ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 7/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step   
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m20/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m26/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m38/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m44/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step
[1m62/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m69/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step
[1m75/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m81/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 43ms/step
[1m  8/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step 
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 15/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[1m 20/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 27/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 33/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[1m 40/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 46/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.1785 - loss: 2.4811
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 28ms/step - accuracy: 0.1785 - loss: 2.4810[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 60/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 67/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 32ms/step - accuracy: 0.2318 - loss: 2.2074 - val_accuracy: 0.2720 - val_loss: 2.0041
[36m(train_cnn_ray_tune pid=1593434)[0m Epoch 19/21
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 76ms/step - accuracy: 0.1562 - loss: 2.2573
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m417/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 26ms/step - accuracy: 0.1871 - loss: 2.4241
[1m420/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 26ms/step - accuracy: 0.1871 - loss: 2.4241[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 79/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  3/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.1632 - loss: 2.3162
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.1607 - loss: 2.3260
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 84/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m 90/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593430)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m   _log_deprecation_warning([32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  8/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1720 - loss: 2.2990
[1m 10/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1794 - loss: 2.2841
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m 96/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m103/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 12/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1835 - loss: 2.2767
[1m 15/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1880 - loss: 2.2696
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[1m117/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 17/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1908 - loss: 2.2630
[1m 19/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1937 - loss: 2.2574
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m124/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m491/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 28ms/step - accuracy: 0.2916 - loss: 2.0512[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m130/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[1m137/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 21/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1961 - loss: 2.2538
[1m 23/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1983 - loss: 2.2516
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m143/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[1m149/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 26/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.2008 - loss: 2.2491
[1m 28/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.2022 - loss: 2.2473
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 17ms/step - accuracy: 0.2005 - loss: 2.3327
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 17ms/step - accuracy: 0.2006 - loss: 2.3327[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m156/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step
[1m162/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 31/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.2040 - loss: 2.2446
[1m 33/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.2052 - loss: 2.2429
[36m(train_cnn_ray_tune pid=1593430)[0m 
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 35/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.2062 - loss: 2.2419
[1m 37/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.2072 - loss: 2.2404

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:15:16. Total running time: 10min 36s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             632.987 │
│ time_total_s                 632.987 │
│ training_iteration                 1 │
│ val_accuracy                 0.37243 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:15:16. Total running time: 10min 36s
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 40/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2089 - loss: 2.2374
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 43/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2104 - loss: 2.2342
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 45/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2113 - loss: 2.2322
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 48/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2123 - loss: 2.2304
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2131 - loss: 2.2295
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 17ms/step - accuracy: 0.2006 - loss: 2.3333[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 53/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2135 - loss: 2.2288
[1m 56/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2142 - loss: 2.2277
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 58/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2145 - loss: 2.2269
[1m 60/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2148 - loss: 2.2261
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 63/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2153 - loss: 2.2250
[1m 65/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 25ms/step - accuracy: 0.2156 - loss: 2.2243
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.1788 - loss: 2.4805[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 68/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2161 - loss: 2.2233
[1m 71/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2165 - loss: 2.2225
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 73/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2168 - loss: 2.2220
[1m 75/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2170 - loss: 2.2213
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 77/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2173 - loss: 2.2206
[1m 79/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2176 - loss: 2.2199
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 81/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2179 - loss: 2.2191
[1m 84/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2184 - loss: 2.2178
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 86/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2188 - loss: 2.2168
[1m 89/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2193 - loss: 2.2155
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 92/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2197 - loss: 2.2144
[1m 95/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2202 - loss: 2.2131
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 98/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 25ms/step - accuracy: 0.2207 - loss: 2.2119
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m101/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.2211 - loss: 2.2108
[1m103/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.2214 - loss: 2.2102
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m106/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.2218 - loss: 2.2093
[1m108/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.2221 - loss: 2.2088
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m111/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.2225 - loss: 2.2082
[1m114/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.2228 - loss: 2.2076
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m117/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.2231 - loss: 2.2069
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 27ms/step - accuracy: 0.4663 - loss: 1.4636 - val_accuracy: 0.3850 - val_loss: 1.8248
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m120/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.2235 - loss: 2.2063
[1m123/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.2238 - loss: 2.2057
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 67ms/step - accuracy: 0.3750 - loss: 1.8107
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 16ms/step - accuracy: 0.3669 - loss: 1.7988 
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m126/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 25ms/step - accuracy: 0.2241 - loss: 2.2050
[1m129/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.2244 - loss: 2.2043
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m132/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 24ms/step - accuracy: 0.2248 - loss: 2.2036
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m135/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.2251 - loss: 2.2029
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m138/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.2254 - loss: 2.2023
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m141/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.2256 - loss: 2.2017
[1m144/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.2259 - loss: 2.2011
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 464ms/step
[1m 7/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step   
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m147/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.2262 - loss: 2.2005
[1m150/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.2264 - loss: 2.2000
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m13/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m19/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m153/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.2266 - loss: 2.1995
[1m156/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.2269 - loss: 2.1990
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m26/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[1m32/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m159/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.2271 - loss: 2.1986
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m38/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m44/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m162/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 24ms/step - accuracy: 0.2273 - loss: 2.1981
[1m165/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.2274 - loss: 2.1978 
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m62/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step
[1m79/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 44ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m  8/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step 
[1m 16/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 7ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.1792 - loss: 2.4799
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 27ms/step - accuracy: 0.1792 - loss: 2.4799[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 31ms/step - accuracy: 0.2917 - loss: 2.0510 - val_accuracy: 0.2453 - val_loss: 2.1872
[36m(train_cnn_ray_tune pid=1593428)[0m Epoch 20/20[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 72ms/step - accuracy: 0.3438 - loss: 1.9440
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 21/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[1m 27/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 16ms/step - accuracy: 0.2011 - loss: 2.3341
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 16ms/step - accuracy: 0.2011 - loss: 2.3341
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 16ms/step - accuracy: 0.2011 - loss: 2.3341
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m218/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 23ms/step - accuracy: 0.2295 - loss: 2.1923
[1m221/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 23ms/step - accuracy: 0.2296 - loss: 2.1920[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.3009 - loss: 2.0550
[1m 10/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.2841 - loss: 2.0785
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 33/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 38/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 12/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.2764 - loss: 2.0888
[1m 15/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.2719 - loss: 2.0897
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 44/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 49/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 18/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.2710 - loss: 2.0868
[1m 21/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2717 - loss: 2.0829
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 28ms/step - accuracy: 0.1874 - loss: 2.4229 - val_accuracy: 0.1915 - val_loss: 2.2371
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 61/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 73ms/step - accuracy: 0.1562 - loss: 2.3446
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 67/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 78/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m241/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 23ms/step - accuracy: 0.2302 - loss: 2.1905[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 83/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 88/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 33/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2757 - loss: 2.0705
[1m 35/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2763 - loss: 2.0695
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m 92/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m 97/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593442)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1998 - loss: 2.2945
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.2027 - loss: 2.2897[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m103/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 10ms/step
[1m109/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m114/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[1m120/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.1557 - loss: 2.5098[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m126/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[1m132/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m138/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[1m143/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m149/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step
[1m155/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.2043 - loss: 2.2739[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m160/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[1m166/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593442)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 10ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:15:22. Total running time: 10min 41s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             638.525 │
│ time_total_s                 638.525 │
│ training_iteration                 1 │
│ val_accuracy                 0.38501 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:15:22. Total running time: 10min 41s
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.1792 - loss: 2.4798[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m102/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.1877 - loss: 2.4310 
[1m105/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.1874 - loss: 2.4315
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 15ms/step - accuracy: 0.3577 - loss: 2.0321 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 14ms/step - accuracy: 0.3335 - loss: 2.0189
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 21ms/step - accuracy: 0.2463 - loss: 2.0880 - val_accuracy: 0.3199 - val_loss: 1.9425[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 58ms/step - accuracy: 0.0625 - loss: 2.4777
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 13ms/step - accuracy: 0.1721 - loss: 2.3429 
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m7s[0m 10ms/step - accuracy: 0.1960 - loss: 2.2685
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m7s[0m 10ms/step - accuracy: 0.1960 - loss: 2.2683[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 15/23[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m243/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 21ms/step - accuracy: 0.2953 - loss: 2.0400
[1m246/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 21ms/step - accuracy: 0.2954 - loss: 2.0399[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m135/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.2909 - loss: 2.0481
[1m138/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 22ms/step - accuracy: 0.2911 - loss: 2.0479[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 68ms/step - accuracy: 0.0625 - loss: 3.1791[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1354 - loss: 2.8656 
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m270/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m5s[0m 19ms/step - accuracy: 0.1814 - loss: 2.4385[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  12/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1585 - loss: 2.7322
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1658 - loss: 2.7027[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m126/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2904 - loss: 2.0487[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 14ms/step - accuracy: 0.2694 - loss: 2.0466[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 15ms/step - accuracy: 0.3602 - loss: 1.7858[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 68ms/step - accuracy: 0.1875 - loss: 2.5397
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 15ms/step - accuracy: 0.1912 - loss: 2.4440 
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m141/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.2913 - loss: 2.0478 
[1m144/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.2914 - loss: 2.0476
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 17ms/step - accuracy: 0.2015 - loss: 2.3348 - val_accuracy: 0.2011 - val_loss: 2.2268[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 25ms/step - accuracy: 0.2356 - loss: 2.1762 - val_accuracy: 0.2949 - val_loss: 1.9907
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 16ms/step - accuracy: 0.3603 - loss: 1.7799
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 16ms/step - accuracy: 0.3603 - loss: 1.7798[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m Epoch 20/21[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m490/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 20ms/step - accuracy: 0.1802 - loss: 2.4361
[1m493/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 20ms/step - accuracy: 0.1802 - loss: 2.4361[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.2070 - loss: 2.1271
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 23ms/step - accuracy: 0.2292 - loss: 2.0981
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 19/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2459 - loss: 2.0838
[1m 22/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2472 - loss: 2.0830
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 25/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2477 - loss: 2.0826
[1m 28/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2477 - loss: 2.0855
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 73ms/step - accuracy: 0.1562 - loss: 2.2724
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m478/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 22ms/step - accuracy: 0.2988 - loss: 2.0288[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 44/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2474 - loss: 2.1030
[1m 47/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2472 - loss: 2.1064
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m20s[0m 22ms/step - accuracy: 0.1768 - loss: 2.4834
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m20s[0m 22ms/step - accuracy: 0.1768 - loss: 2.4830[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2469 - loss: 2.1097
[1m 53/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2466 - loss: 2.1126
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 56/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2463 - loss: 2.1155[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 59/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2460 - loss: 2.1180
[1m 62/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2458 - loss: 2.1203
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 65/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2456 - loss: 2.1227
[1m 68/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2454 - loss: 2.1251
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m20s[0m 23ms/step - accuracy: 0.1767 - loss: 2.4806[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 74/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2451 - loss: 2.1289
[1m 77/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2448 - loss: 2.1308
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 79/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2447 - loss: 2.1320
[1m 82/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2445 - loss: 2.1336
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 85/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2443 - loss: 2.1351
[1m 88/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2442 - loss: 2.1366
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 15ms/step - accuracy: 0.2696 - loss: 2.0449[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 90/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2441 - loss: 2.1374
[1m 93/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2440 - loss: 2.1387
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 96/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2439 - loss: 2.1398
[1m 99/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2438 - loss: 2.1408
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m105/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2436 - loss: 2.1427
[1m108/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 23ms/step - accuracy: 0.2436 - loss: 2.1435
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m111/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2435 - loss: 2.1443
[1m114/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2436 - loss: 2.1450
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m120/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2436 - loss: 2.1462
[1m123/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2436 - loss: 2.1468
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m125/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2436 - loss: 2.1472
[1m128/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2436 - loss: 2.1477
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m131/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2436 - loss: 2.1482
[1m134/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2436 - loss: 2.1487
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m137/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2435 - loss: 2.1492
[1m140/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2435 - loss: 2.1498
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m143/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2434 - loss: 2.1504
[1m146/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2433 - loss: 2.1510
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m149/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 23ms/step - accuracy: 0.2433 - loss: 2.1515 
[1m152/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 23ms/step - accuracy: 0.2432 - loss: 2.1520
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 14ms/step - accuracy: 0.1988 - loss: 2.3687 
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 14ms/step - accuracy: 0.1988 - loss: 2.3684
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 69ms/step - accuracy: 0.0625 - loss: 2.6093
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 23ms/step - accuracy: 0.1798 - loss: 2.4347 - val_accuracy: 0.1956 - val_loss: 2.2230
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 26ms/step - accuracy: 0.2999 - loss: 2.0268 - val_accuracy: 0.2376 - val_loss: 2.1880
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 12ms/step - accuracy: 0.1965 - loss: 2.2670 - val_accuracy: 0.2226 - val_loss: 2.1816
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.2692 - loss: 2.0437
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.2692 - loss: 2.0437[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m Epoch 23/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.1875 - loss: 1.9641
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.2465 - loss: 2.1032 
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 64/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.1592 - loss: 2.4315
[1m 67/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.1599 - loss: 2.4313[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 52/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 19ms/step - accuracy: 0.1555 - loss: 2.4330
[1m 55/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 19ms/step - accuracy: 0.1564 - loss: 2.4330 [32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 472ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 6/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step  
[1m12/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m24/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m279/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.2402 - loss: 2.1588[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m35/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m40/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.2153 - loss: 2.2062
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.2152 - loss: 2.2077[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m57/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m69/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m117/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 23ms/step - accuracy: 0.2436 - loss: 2.1456[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m80/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[1m85/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 22ms/step - accuracy: 0.1762 - loss: 2.4696[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 15ms/step - accuracy: 0.2691 - loss: 2.0432[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 42ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m  7/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 12/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 18/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 24/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 29/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 35/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 40/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 45/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 51/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 57/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 63/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 68/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 74/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.2101 - loss: 2.2263
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.2100 - loss: 2.2266
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.2100 - loss: 2.2269
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 80/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 86/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m 92/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m 98/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m104/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 10ms/step
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m116/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 10ms/step
[1m122/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m128/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[1m134/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m140/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 10ms/step
[1m145/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m151/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 10ms/step
[1m157/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m163/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593428)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 10ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:15:39. Total running time: 10min 58s
[36m(train_cnn_ray_tune pid=1593428)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593428)[0m   _log_deprecation_warning(
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             655.718 │
│ time_total_s                 655.718 │
│ training_iteration                 1 │
│ val_accuracy                 0.23756 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:15:39. Total running time: 10min 58s
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 18ms/step - accuracy: 0.3603 - loss: 1.7754 - val_accuracy: 0.3684 - val_loss: 1.7745
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.2022 - loss: 2.3508
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.2022 - loss: 2.3507[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m Epoch 16/21
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.3125 - loss: 2.0120
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.3187 - loss: 2.0781 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.1767 - loss: 2.4647 
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.1767 - loss: 2.4646
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m338/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m4s[0m 19ms/step - accuracy: 0.1767 - loss: 2.4224
[1m341/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m4s[0m 19ms/step - accuracy: 0.1767 - loss: 2.4223[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m534/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 21ms/step - accuracy: 0.2391 - loss: 2.1620[32m [repeated 37x across cluster][0m

Trial status: 13 TERMINATED | 7 RUNNING
Current time: 2025-10-31 15:15:41. Total running time: 11min 1s
Logical resource usage: 7.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23                                              │
│ trial_8b084    RUNNING              3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 16                  3                 1          0.000172735         21                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27                                              │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24        1            607.522         0.187419 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29        1            632.987         0.372433 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29        1            562.331         0.177428 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18        1            590.703         0.203515 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20        1            655.718         0.237558 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   16                 64                  3                 0          0.000176203         22        1            611.614         0.258094 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22        1            638.525         0.385014 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15        1            508.648         0.209991 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17        1            577.082         0.245513 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 14ms/step - accuracy: 0.3585 - loss: 1.7941
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 14ms/step - accuracy: 0.3583 - loss: 1.7937[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 15ms/step - accuracy: 0.3571 - loss: 1.7914[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.2072 - loss: 2.2371[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 17ms/step - accuracy: 0.2692 - loss: 2.0422 - val_accuracy: 0.3343 - val_loss: 1.9278
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 16/23
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 67ms/step - accuracy: 0.4375 - loss: 1.8938
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 14ms/step - accuracy: 0.3113 - loss: 2.0492 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 13ms/step - accuracy: 0.3033 - loss: 2.0548
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 24ms/step - accuracy: 0.2390 - loss: 2.1621 - val_accuracy: 0.2894 - val_loss: 1.9853
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 73ms/step - accuracy: 0.1875 - loss: 2.0057
[1m  4/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2188 - loss: 2.1286
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  7/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2266 - loss: 2.1564
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 10/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 21ms/step - accuracy: 0.2317 - loss: 2.1716
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 13/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 21ms/step - accuracy: 0.2376 - loss: 2.1704
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 16/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 21ms/step - accuracy: 0.2420 - loss: 2.1647
[1m 19/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 21ms/step - accuracy: 0.2457 - loss: 2.1629
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 22/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2493 - loss: 2.1603
[1m 25/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2520 - loss: 2.1589
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 28/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2539 - loss: 2.1577
[1m 31/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2549 - loss: 2.1563
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 34/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2555 - loss: 2.1548
[1m 37/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2561 - loss: 2.1535
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 40/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2567 - loss: 2.1523
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 43/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2572 - loss: 2.1505
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 46/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2577 - loss: 2.1489
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 49/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2579 - loss: 2.1477
[1m 52/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2580 - loss: 2.1472
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 55/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 21ms/step - accuracy: 0.2580 - loss: 2.1469
[1m 58/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2581 - loss: 2.1464
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 61/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2581 - loss: 2.1462
[1m 64/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2580 - loss: 2.1459
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 67/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2579 - loss: 2.1457
[1m 70/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2577 - loss: 2.1458
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 73/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2575 - loss: 2.1459
[1m 76/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2573 - loss: 2.1460
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.2054 - loss: 2.2413
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.2054 - loss: 2.2414[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 79/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2571 - loss: 2.1462
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 82/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2569 - loss: 2.1462
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m581/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 18ms/step - accuracy: 0.1797 - loss: 2.4182
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 18ms/step - accuracy: 0.1798 - loss: 2.4182[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 85/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2568 - loss: 2.1461
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 88/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2567 - loss: 2.1462
[1m 91/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2566 - loss: 2.1464
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 94/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2564 - loss: 2.1467
[1m 97/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2563 - loss: 2.1469
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m100/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2561 - loss: 2.1471
[1m103/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.2559 - loss: 2.1471 
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m578/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 18ms/step - accuracy: 0.1797 - loss: 2.4182[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 14ms/step - accuracy: 0.2749 - loss: 2.0401
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 14ms/step - accuracy: 0.2749 - loss: 2.0400[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 15ms/step - accuracy: 0.3565 - loss: 1.7696[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 21ms/step - accuracy: 0.1778 - loss: 2.4601[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m18s[0m 15ms/step - accuracy: 0.2029 - loss: 2.3472 - val_accuracy: 0.2061 - val_loss: 2.2230
[36m(train_cnn_ray_tune pid=1593439)[0m Epoch 25/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 79ms/step - accuracy: 0.2812 - loss: 2.2431[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.1873 - loss: 2.3893 
[1m  10/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.1874 - loss: 2.3560
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 21ms/step - accuracy: 0.1798 - loss: 2.4182 - val_accuracy: 0.1909 - val_loss: 2.2151
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 85/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.1867 - loss: 2.3637 [32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 79/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.1874 - loss: 2.3619
[1m 82/584[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 20ms/step - accuracy: 0.1870 - loss: 2.3628[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 12ms/step - accuracy: 0.2047 - loss: 2.2427 - val_accuracy: 0.2216 - val_loss: 2.1822
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 14ms/step - accuracy: 0.2747 - loss: 2.0383 
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 14ms/step - accuracy: 0.2746 - loss: 2.0383
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2387 - loss: 2.2527 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2304 - loss: 2.2410
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 14ms/step - accuracy: 0.2747 - loss: 2.0377
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 14ms/step - accuracy: 0.2747 - loss: 2.0377[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m191/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 20ms/step - accuracy: 0.1819 - loss: 2.3810
[1m195/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 20ms/step - accuracy: 0.1819 - loss: 2.3813[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m349/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m4s[0m 21ms/step - accuracy: 0.2490 - loss: 2.1518[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2101 - loss: 2.2579 
[1m 170/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2102 - loss: 2.2578
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.2044 - loss: 2.3197 
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.2045 - loss: 2.3198
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.2045 - loss: 2.3199
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 14ms/step - accuracy: 0.2044 - loss: 2.3195
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 14ms/step - accuracy: 0.2044 - loss: 2.3196[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.2164 - loss: 2.2421[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.3616 - loss: 1.7514[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m Epoch 24/25
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 71ms/step - accuracy: 0.2500 - loss: 2.2915
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 12/22
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 67ms/step - accuracy: 0.1250 - loss: 2.7370
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1302 - loss: 2.7103 
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2092 - loss: 2.2502[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.2092 - loss: 2.2500
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.2092 - loss: 2.2499[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 24ms/step - accuracy: 0.1784 - loss: 2.4588 - val_accuracy: 0.1824 - val_loss: 2.1794
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step - accuracy: 0.3626 - loss: 1.7475
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step - accuracy: 0.3626 - loss: 1.7474[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m485/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 18ms/step - accuracy: 0.1828 - loss: 2.3880
[1m488/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 18ms/step - accuracy: 0.1828 - loss: 2.3880[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m511/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 18ms/step - accuracy: 0.1827 - loss: 2.3884[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 140/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 22ms/step - accuracy: 0.1739 - loss: 2.4536
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 21ms/step - accuracy: 0.1739 - loss: 2.4534[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 21ms/step - accuracy: 0.1738 - loss: 2.4523[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 23ms/step - accuracy: 0.2497 - loss: 2.1482 - val_accuracy: 0.3060 - val_loss: 1.9686
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 13ms/step - accuracy: 0.2063 - loss: 2.3199[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 474ms/step
[1m 8/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step   
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m27/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m34/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 8ms/step
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m75/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step
[1m82/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 17ms/step - accuracy: 0.3628 - loss: 1.7468 - val_accuracy: 0.3565 - val_loss: 1.7856
[36m(train_cnn_ray_tune pid=1593436)[0m Epoch 17/21
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 57ms/step - accuracy: 0.4375 - loss: 1.4390
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.4552 - loss: 1.4255 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 11ms/step - accuracy: 0.4515 - loss: 1.4653
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 70ms/step - accuracy: 0.2500 - loss: 2.3942
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 15ms/step - accuracy: 0.1754 - loss: 2.4813 
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 48ms/step
[1m  7/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2084 - loss: 2.2448
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 13/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 19/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 26/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 32/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2082 - loss: 2.2446
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2082 - loss: 2.2446[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 38/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[1m 45/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 51/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 58/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2082 - loss: 2.2445
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 65/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593434)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 71/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 77/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 84/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 91/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m 98/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 8ms/step
[1m104/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[1m117/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m123/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 8ms/step
[1m130/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m136/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[1m142/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m149/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 8ms/step
[1m156/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m163/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step
[36m(train_cnn_ray_tune pid=1593434)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:16:00. Total running time: 11min 20s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             677.558 │
│ time_total_s                 677.558 │
│ training_iteration                 1 │
│ val_accuracy                 0.30601 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:16:00. Total running time: 11min 20s
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.2066 - loss: 2.3181
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.2066 - loss: 2.3181[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m124/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 16ms/step - accuracy: 0.1829 - loss: 2.3931
[1m128/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 16ms/step - accuracy: 0.1828 - loss: 2.3928[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m104/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m7s[0m 16ms/step - accuracy: 0.1832 - loss: 2.3944[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 11ms/step - accuracy: 0.2853 - loss: 1.9731
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 11ms/step - accuracy: 0.2856 - loss: 1.9724[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.3877 - loss: 1.6726[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 11ms/step - accuracy: 0.2081 - loss: 2.2443 - val_accuracy: 0.2161 - val_loss: 2.1796
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 20ms/step - accuracy: 0.1826 - loss: 2.3894 - val_accuracy: 0.1985 - val_loss: 2.2015
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.2066 - loss: 2.3180[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2251 - loss: 2.2503
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 18ms/step - accuracy: 0.1731 - loss: 2.4551
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 18ms/step - accuracy: 0.1731 - loss: 2.4550
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 18ms/step - accuracy: 0.1731 - loss: 2.4550
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2218 - loss: 2.2354
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m17s[0m 14ms/step - accuracy: 0.2066 - loss: 2.3180 - val_accuracy: 0.2019 - val_loss: 2.2238[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m Epoch 25/25[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.3125 - loss: 2.4040
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.2851 - loss: 2.3399 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.2582 - loss: 2.3397
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.1250 - loss: 2.6656
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2045 - loss: 2.3957  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2193 - loss: 2.2351
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2186 - loss: 2.2345
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2185 - loss: 2.2344[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2180 - loss: 2.2339
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 11ms/step - accuracy: 0.2205 - loss: 2.2935 
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 11ms/step - accuracy: 0.2205 - loss: 2.2935
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2171 - loss: 2.2328
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2170 - loss: 2.2327
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2170 - loss: 2.2326
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.2930 - loss: 1.9794
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.2930 - loss: 1.9795[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m452/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 15ms/step - accuracy: 0.1861 - loss: 2.3812
[1m456/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.1862 - loss: 2.3811[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 18ms/step - accuracy: 0.1740 - loss: 2.4525
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 18ms/step - accuracy: 0.1740 - loss: 2.4524
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 18ms/step - accuracy: 0.1740 - loss: 2.4524
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m476/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 15ms/step - accuracy: 0.1864 - loss: 2.3806[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.2157 - loss: 2.2318
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.2203 - loss: 2.2937
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.2204 - loss: 2.2936[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.2922 - loss: 1.9782[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.2147 - loss: 2.2318
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.3832 - loss: 1.6880[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.2194 - loss: 2.2945
[1m 223/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.2195 - loss: 2.2945
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.2196 - loss: 2.2945
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 18ms/step - accuracy: 0.1872 - loss: 2.3792 - val_accuracy: 0.1993 - val_loss: 2.1905
[36m(train_cnn_ray_tune pid=1593439)[0m Epoch 27/28
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 69ms/step - accuracy: 0.1875 - loss: 2.5015
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2136 - loss: 2.2319
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2136 - loss: 2.2319[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2138 - loss: 2.2318[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.2921 - loss: 1.9845
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.2921 - loss: 1.9845[32m [repeated 168x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m102/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m7s[0m 15ms/step - accuracy: 0.1705 - loss: 2.4340
[1m106/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m7s[0m 15ms/step - accuracy: 0.1711 - loss: 2.4329[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.1750 - loss: 2.4489
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.1750 - loss: 2.4488
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 18ms/step - accuracy: 0.1750 - loss: 2.4488[32m [repeated 2x across cluster][0m

Trial status: 14 TERMINATED | 6 RUNNING
Current time: 2025-10-31 15:16:11. Total running time: 11min 31s
Logical resource usage: 6.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25                                              │
│ trial_8b084    RUNNING              2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 16                  3                 1          0.000172735         21                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27                                              │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24        1            607.522         0.187419 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29        1            632.987         0.372433 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29        1            562.331         0.177428 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18        1            590.703         0.203515 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21        1            677.558         0.306013 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20        1            655.718         0.237558 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   16                 64                  3                 0          0.000176203         22        1            611.614         0.258094 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22        1            638.525         0.385014 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15        1            508.648         0.209991 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17        1            577.082         0.245513 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m110/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m7s[0m 15ms/step - accuracy: 0.1716 - loss: 2.4319[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.2922 - loss: 1.9852[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 10ms/step - accuracy: 0.2131 - loss: 2.2319 - val_accuracy: 0.2200 - val_loss: 2.1827
[36m(train_cnn_ray_tune pid=1593421)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593421)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 259ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m22/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step   
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m45/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 14ms/step - accuracy: 0.3808 - loss: 1.6966 - val_accuracy: 0.3623 - val_loss: 1.8081
[36m(train_cnn_ray_tune pid=1593436)[0m Epoch 18/21
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 5ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.7500 - loss: 1.1041
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 7ms/step - accuracy: 0.4881 - loss: 1.5710  
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 7ms/step - accuracy: 0.4443 - loss: 1.6403
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 7ms/step - accuracy: 0.4319 - loss: 1.6526[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 31ms/step
[1m 22/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step 
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 43/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step
[1m 66/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2131 - loss: 2.2319[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m 88/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step
[1m111/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m134/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step
[1m156/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 37ms/step - accuracy: 0.4375 - loss: 1.6984
[36m(train_cnn_ray_tune pid=1593421)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:16:15. Total running time: 11min 35s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             692.143 │
│ time_total_s                 692.143 │
│ training_iteration                 1 │
│ val_accuracy                 0.21998 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:16:15. Total running time: 11min 35s
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 7ms/step - accuracy: 0.2752 - loss: 1.8085  
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2949 - loss: 1.7954
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 11ms/step - accuracy: 0.3004 - loss: 2.0068
[1m  17/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.2878 - loss: 2.0460
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 16ms/step - accuracy: 0.1716 - loss: 2.2811
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.2192 - loss: 2.2926
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.2192 - loss: 2.2926[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m528/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 13ms/step - accuracy: 0.1854 - loss: 2.3945
[1m532/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 13ms/step - accuracy: 0.1854 - loss: 2.3943[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 16ms/step - accuracy: 0.1962 - loss: 2.2784
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m500/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 13ms/step - accuracy: 0.1851 - loss: 2.3955[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.2192 - loss: 2.2926[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m9s[0m 15ms/step - accuracy: 0.1860 - loss: 2.3923 - val_accuracy: 0.2048 - val_loss: 2.1798
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  5/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 15ms/step - accuracy: 0.1688 - loss: 2.4769 
[1m  9/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 14ms/step - accuracy: 0.1657 - loss: 2.4558
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m8s[0m 10ms/step - accuracy: 0.2385 - loss: 2.2406
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m8s[0m 10ms/step - accuracy: 0.2383 - loss: 2.2410
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 10ms/step - accuracy: 0.2381 - loss: 2.2414
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 19ms/step - accuracy: 0.1758 - loss: 2.4464 - val_accuracy: 0.1930 - val_loss: 2.1628[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m Epoch 28/28[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 49ms/step - accuracy: 0.2500 - loss: 1.8784
[1m   4/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 18ms/step - accuracy: 0.1914 - loss: 2.1540[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 10ms/step - accuracy: 0.3975 - loss: 1.6832
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 10ms/step - accuracy: 0.3974 - loss: 1.6833[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.3984 - loss: 1.6821[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 63ms/step - accuracy: 0.1562 - loss: 2.3755
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 15ms/step - accuracy: 0.1995 - loss: 2.3393
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 15ms/step - accuracy: 0.1995 - loss: 2.3398[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 15ms/step - accuracy: 0.1993 - loss: 2.3406[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.2983 - loss: 1.9415
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.2983 - loss: 1.9416[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m197/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 14ms/step - accuracy: 0.1888 - loss: 2.3767
[1m201/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 14ms/step - accuracy: 0.1888 - loss: 2.3765[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m241/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m4s[0m 14ms/step - accuracy: 0.1893 - loss: 2.3745[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.2985 - loss: 1.9431[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 15ms/step - accuracy: 0.1959 - loss: 2.3587
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 15ms/step - accuracy: 0.1959 - loss: 2.3590[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 15ms/step - accuracy: 0.1958 - loss: 2.3594 [32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.3001 - loss: 1.9453
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.3001 - loss: 1.9453[32m [repeated 132x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m569/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step - accuracy: 0.1900 - loss: 2.3667
[1m573/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step - accuracy: 0.1900 - loss: 2.3667[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m509/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 14ms/step - accuracy: 0.1898 - loss: 2.3675[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 16ms/step - accuracy: 0.1900 - loss: 2.3666 - val_accuracy: 0.2056 - val_loss: 2.1744
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.3921 - loss: 1.6833[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 449ms/step
[1m11/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step   
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m32/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 5ms/step
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m84/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 11ms/step - accuracy: 0.2280 - loss: 2.2651 - val_accuracy: 0.2041 - val_loss: 2.2106
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 22/27
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 52ms/step - accuracy: 0.3125 - loss: 2.1247
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2355 - loss: 2.2952   
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2243 - loss: 2.3120
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2238 - loss: 2.2979
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2252 - loss: 2.2810
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2247 - loss: 2.2730
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 39ms/step
[1m 11/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step 
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2255 - loss: 2.2663
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2260 - loss: 2.2614
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 21/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m 31/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2258 - loss: 2.2580
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2255 - loss: 2.2560
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 41/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m 51/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  66/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2255 - loss: 2.2544
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2258 - loss: 2.2527
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 61/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m 70/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1593439)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593439)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2264 - loss: 2.2507
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2491
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 79/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m 88/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  90/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2486
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2490
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m 97/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m106/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2498
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2504
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m116/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 6ms/step
[1m126/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2507
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2508
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m135/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 6ms/step
[1m144/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2270 - loss: 2.2510
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2271 - loss: 2.2515
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m152/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 6ms/step
[1m161/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2271 - loss: 2.2519
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2271 - loss: 2.2522
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2271 - loss: 2.2522
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2271 - loss: 2.2523

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:16:30. Total running time: 11min 49s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             706.591 │
│ time_total_s                 706.591 │
│ training_iteration                 1 │
│ val_accuracy                 0.20555 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:16:30. Total running time: 11min 49s
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2270 - loss: 2.2524
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2524
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 172/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2526
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2527
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2528
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2529
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2530
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2529
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 10ms/step - accuracy: 0.3168 - loss: 1.9265
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 10ms/step - accuracy: 0.3162 - loss: 1.9275[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2528
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2527
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2526
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2525
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.3784 - loss: 1.6799
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2524
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2523
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2522
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2521
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 171/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.3145 - loss: 1.9279
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.3144 - loss: 1.9277[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2520
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2519
[36m(train_cnn_ray_tune pid=1593439)[0m 
[1m577/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step - accuracy: 0.1900 - loss: 2.3667
[1m581/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step - accuracy: 0.1900 - loss: 2.3666
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2518
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2518
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2518
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2518
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2519
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2519
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2520
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2269 - loss: 2.2521
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2522
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2523
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2268 - loss: 2.2524
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2267 - loss: 2.2525
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2267 - loss: 2.2526
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2267 - loss: 2.2526
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2266 - loss: 2.2527
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2266 - loss: 2.2527
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2265 - loss: 2.2528
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2265 - loss: 2.2529
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2264 - loss: 2.2530
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2264 - loss: 2.2531
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2263 - loss: 2.2532
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2262 - loss: 2.2533
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2262 - loss: 2.2534
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2261 - loss: 2.2536
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2260 - loss: 2.2537
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2260 - loss: 2.2538
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2259 - loss: 2.2539
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2259 - loss: 2.2540
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2258 - loss: 2.2542
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.3131 - loss: 1.9254 
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.3131 - loss: 1.9254
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 10ms/step - accuracy: 0.3131 - loss: 1.9254[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2257 - loss: 2.2544
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2256 - loss: 2.2547
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 12ms/step - accuracy: 0.3006 - loss: 1.9456 - val_accuracy: 0.3508 - val_loss: 1.8659[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 19/23[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.2234 - loss: 2.2589
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.2233 - loss: 2.2591
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.2232 - loss: 2.2594
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.3125 - loss: 2.0705
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 10ms/step - accuracy: 0.3253 - loss: 1.9851 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.3133 - loss: 1.9236
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m4s[0m 8ms/step - accuracy: 0.3133 - loss: 1.9236[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 44ms/step - accuracy: 0.1875 - loss: 2.1466
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2046 - loss: 2.3513
[1m 117/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2044 - loss: 2.3519[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 8ms/step - accuracy: 0.2212 - loss: 2.2641
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2049 - loss: 2.3507
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m7s[0m 10ms/step - accuracy: 0.3846 - loss: 1.6683
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.3847 - loss: 1.6682 [32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 13ms/step - accuracy: 0.2002 - loss: 2.3717
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 8ms/step - accuracy: 0.2209 - loss: 2.2656
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step - accuracy: 0.2210 - loss: 2.2657
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.1983 - loss: 2.3833
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.1982 - loss: 2.3837
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.1982 - loss: 2.3840
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m19s[0m 16ms/step - accuracy: 0.1887 - loss: 2.3848 - val_accuracy: 0.1919 - val_loss: 2.1560
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 14/22
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.1981 - loss: 2.3844
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.1981 - loss: 2.3847
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step - accuracy: 0.3121 - loss: 1.9227
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step - accuracy: 0.3121 - loss: 1.9227[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.1976 - loss: 2.3878 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.1975 - loss: 2.3881
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.1975 - loss: 2.3885
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 9ms/step - accuracy: 0.2210 - loss: 2.2657 - val_accuracy: 0.2105 - val_loss: 2.2114
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 23/27
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 53ms/step - accuracy: 0.1875 - loss: 2.4329
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2017 - loss: 2.3984   
[1m  15/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2174 - loss: 2.3491
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.1970 - loss: 2.3914
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.1970 - loss: 2.3917
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.1969 - loss: 2.3920
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 13ms/step - accuracy: 0.1966 - loss: 2.3939
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 13ms/step - accuracy: 0.1965 - loss: 2.3941
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.1977 - loss: 2.3872
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.1976 - loss: 2.3875[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 13ms/step - accuracy: 0.1965 - loss: 2.3943
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 51ms/step - accuracy: 0.3125 - loss: 2.6101
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.3063 - loss: 2.1805
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2831 - loss: 2.1326 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2885 - loss: 2.0992
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2948 - loss: 2.0749
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2997 - loss: 2.0554[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.1963 - loss: 2.3956
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.1963 - loss: 2.3957

Trial status: 16 TERMINATED | 4 RUNNING
Current time: 2025-10-31 15:16:41. Total running time: 12min 1s
Logical resource usage: 4.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 16                  3                 1          0.000172735         21                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27                                              │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24        1            607.522         0.187419 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25        1            692.143         0.219981 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29        1            632.987         0.372433 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29        1            562.331         0.177428 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18        1            590.703         0.203515 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21        1            677.558         0.306013 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20        1            655.718         0.237558 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   16                 64                  3                 0          0.000176203         22        1            611.614         0.258094 │
│ trial_8b084    TERMINATED           3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28        1            706.591         0.20555  │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22        1            638.525         0.385014 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15        1            508.648         0.209991 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17        1            577.082         0.245513 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m  34/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.3821 - loss: 1.6246
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.3832 - loss: 1.6307
[1m  44/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.3842 - loss: 1.6336
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m7s[0m 13ms/step - accuracy: 0.1959 - loss: 2.3970
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.3002 - loss: 1.9724[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 10ms/step - accuracy: 0.3890 - loss: 1.6342
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 10ms/step - accuracy: 0.3901 - loss: 1.6336
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.3054 - loss: 1.9493
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.3056 - loss: 1.9485[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 13ms/step - accuracy: 0.1953 - loss: 2.3991[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 11ms/step - accuracy: 0.3881 - loss: 1.6673 - val_accuracy: 0.3748 - val_loss: 1.7504[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m Epoch 20/21[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 10ms/step - accuracy: 0.3965 - loss: 1.6365
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.3966 - loss: 1.6370 [32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.3750 - loss: 1.6588
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.3632 - loss: 1.6408 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 13ms/step - accuracy: 0.1949 - loss: 2.3997
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 13ms/step - accuracy: 0.1949 - loss: 2.3997[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 9ms/step - accuracy: 0.3103 - loss: 1.9282[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.2287 - loss: 2.2520
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.2287 - loss: 2.2520
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.2287 - loss: 2.2520
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 13ms/step - accuracy: 0.1946 - loss: 2.3993
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 13ms/step - accuracy: 0.1946 - loss: 2.3993
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 13ms/step - accuracy: 0.1946 - loss: 2.3993
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.3110 - loss: 1.9233
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.3110 - loss: 1.9232[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 13ms/step - accuracy: 0.1948 - loss: 2.3995[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.3959 - loss: 1.6441 
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.3959 - loss: 1.6441
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 9ms/step - accuracy: 0.2283 - loss: 2.2518 - val_accuracy: 0.2102 - val_loss: 2.2139
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 24/27
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 35ms/step - accuracy: 0.1875 - loss: 2.2116
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2412 - loss: 2.1875  
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2405 - loss: 2.2075
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m17s[0m 14ms/step - accuracy: 0.1943 - loss: 2.3988 - val_accuracy: 0.1948 - val_loss: 2.1438
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.1875 - loss: 1.9878
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.1977 - loss: 2.2186
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.2052 - loss: 2.2347
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.2063 - loss: 2.2534
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.2034 - loss: 2.2643
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.2008 - loss: 2.2709
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1977 - loss: 2.2788
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1956 - loss: 2.2881
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  40/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1938 - loss: 2.2963
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.3960 - loss: 1.6440
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.3960 - loss: 1.6441[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1927 - loss: 2.3029
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1922 - loss: 2.3066
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1919 - loss: 2.3095
[1m  59/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1916 - loss: 2.3126
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  64/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1915 - loss: 2.3147
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1916 - loss: 2.3157
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1916 - loss: 2.3175
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1918 - loss: 2.3192
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1921 - loss: 2.3205
[1m  88/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1922 - loss: 2.3223
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  92/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1923 - loss: 2.3233
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1922 - loss: 2.3244
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1922 - loss: 2.3252
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1922 - loss: 2.3262
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1921 - loss: 2.3274
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 116/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1919 - loss: 2.3285
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1920 - loss: 2.3293
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.4701 - loss: 1.6271  
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.4249 - loss: 1.7136
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1921 - loss: 2.3301
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1921 - loss: 2.3308
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1923 - loss: 2.3317
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1924 - loss: 2.3324
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.3957 - loss: 1.6444[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1926 - loss: 2.3331
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1928 - loss: 2.3338
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1930 - loss: 2.3343
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1932 - loss: 2.3347
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1933 - loss: 2.3352
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1934 - loss: 2.3357
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1935 - loss: 2.3362
[1m 173/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1935 - loss: 2.3366
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1936 - loss: 2.3370
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1936 - loss: 2.3374
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1937 - loss: 2.3378
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1938 - loss: 2.3381
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1939 - loss: 2.3383
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1939 - loss: 2.3384
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3386
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3387
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1941 - loss: 2.3388
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1942 - loss: 2.3389
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1943 - loss: 2.3390
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1943 - loss: 2.3391
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1944 - loss: 2.3392
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1944 - loss: 2.3394
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1944 - loss: 2.3396
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1945 - loss: 2.3397
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 8ms/step - accuracy: 0.2341 - loss: 2.2426
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 8ms/step - accuracy: 0.2340 - loss: 2.2425
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m5s[0m 8ms/step - accuracy: 0.2340 - loss: 2.2424
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 13ms/step - accuracy: 0.1948 - loss: 2.3407
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.3292 - loss: 1.8842
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.3292 - loss: 1.8841[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.4255 - loss: 1.5661 
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.4253 - loss: 1.5662
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 10ms/step - accuracy: 0.3957 - loss: 1.6444 - val_accuracy: 0.3774 - val_loss: 1.7687[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m Epoch 21/21[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 54ms/step - accuracy: 0.6250 - loss: 1.3934
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 57ms/step - accuracy: 0.1250 - loss: 1.6350
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.3144 - loss: 1.6690 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.1956 - loss: 2.3478
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.1957 - loss: 2.3479 [32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.1959 - loss: 2.3487
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.1959 - loss: 2.3485
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.1959 - loss: 2.3486[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 8ms/step - accuracy: 0.2321 - loss: 2.2391[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.3280 - loss: 1.8812
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.3280 - loss: 1.8811[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 13ms/step - accuracy: 0.1957 - loss: 2.3561
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 13ms/step - accuracy: 0.1957 - loss: 2.3562
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 13ms/step - accuracy: 0.1956 - loss: 2.3563
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 13ms/step - accuracy: 0.1955 - loss: 2.3571[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 13ms/step - accuracy: 0.1954 - loss: 2.3571
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 13ms/step - accuracy: 0.1954 - loss: 2.3572[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 10ms/step - accuracy: 0.2308 - loss: 2.2372 - val_accuracy: 0.2124 - val_loss: 2.2042
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 25/27
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 59ms/step - accuracy: 0.5000 - loss: 1.9866
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2970 - loss: 2.2369  
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2636 - loss: 2.2584
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  32/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2431 - loss: 2.2448 
[1m  38/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2409 - loss: 2.2412
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.3278 - loss: 1.8786[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 8ms/step - accuracy: 0.2341 - loss: 2.2171
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 8ms/step - accuracy: 0.2341 - loss: 2.2173[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.3736 - loss: 1.9045  
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.3357 - loss: 1.8694[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 11ms/step - accuracy: 0.4117 - loss: 1.6025 - val_accuracy: 0.3993 - val_loss: 1.7577
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 13ms/step - accuracy: 0.1942 - loss: 2.3620
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 13ms/step - accuracy: 0.1942 - loss: 2.3621[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 310ms/step
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step   
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 10ms/step - accuracy: 0.3278 - loss: 1.8776 - val_accuracy: 0.3593 - val_loss: 1.7640
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 22/23
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.4375 - loss: 1.7495
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[1m62/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m82/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 16/22
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.3351 - loss: 1.8635 
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.3350 - loss: 1.8615
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.1250 - loss: 2.3700
[1m   5/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.1460 - loss: 2.4656
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   9/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.1743 - loss: 2.4307
[1m  14/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.1969 - loss: 2.3990
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.2081 - loss: 2.3788
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.2125 - loss: 2.3661
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 42ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2133 - loss: 2.3605
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2129 - loss: 2.3558
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 7ms/step - accuracy: 0.3340 - loss: 1.8524[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 13/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step 
[1m 24/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  35/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2122 - loss: 2.3532
[1m  39/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2104 - loss: 2.3532
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 37/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m 50/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593436)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593436)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2084 - loss: 2.3541
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2055 - loss: 2.3556
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 62/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m 74/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2036 - loss: 2.3570
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2021 - loss: 2.3586
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m 86/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m 98/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  60/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.2008 - loss: 2.3592
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1995 - loss: 2.3598
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m121/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 4ms/step
[1m134/169[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1985 - loss: 2.3606
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1977 - loss: 2.3613
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m146/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 4ms/step
[1m159/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1970 - loss: 2.3622
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1962 - loss: 2.3630
[36m(train_cnn_ray_tune pid=1593436)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 5ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1957 - loss: 2.3639
[1m  90/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1951 - loss: 2.3645

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:17:08. Total running time: 12min 27s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             744.741 │
│ time_total_s                 744.741 │
│ training_iteration                 1 │
│ val_accuracy                 0.39926 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:17:08. Total running time: 12min 27s
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1945 - loss: 2.3650
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1941 - loss: 2.3656
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1939 - loss: 2.3658
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1936 - loss: 2.3662
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1933 - loss: 2.3670
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1930 - loss: 2.3680
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1927 - loss: 2.3688
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.1925 - loss: 2.3694
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 13ms/step - accuracy: 0.1924 - loss: 2.3699
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 13ms/step - accuracy: 0.1922 - loss: 2.3707
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 143/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 13ms/step - accuracy: 0.1920 - loss: 2.3715
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1920 - loss: 2.3722
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1920 - loss: 2.3727
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1920 - loss: 2.3732
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1920 - loss: 2.3737
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1921 - loss: 2.3741
[1m 173/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1921 - loss: 2.3743
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 7ms/step - accuracy: 0.2350 - loss: 2.2194
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 7ms/step - accuracy: 0.2350 - loss: 2.2194[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1922 - loss: 2.3745
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1923 - loss: 2.3745
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1925 - loss: 2.3745
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1925 - loss: 2.3745
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1926 - loss: 2.3745
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1926 - loss: 2.3745
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1926 - loss: 2.3745
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1926 - loss: 2.3746
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1926 - loss: 2.3746
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 223/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1926 - loss: 2.3745
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1926 - loss: 2.3743
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1926 - loss: 2.3742
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1927 - loss: 2.3739
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1927 - loss: 2.3736
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1928 - loss: 2.3733
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1928 - loss: 2.3731
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1929 - loss: 2.3727
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1930 - loss: 2.3723
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1931 - loss: 2.3720
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1931 - loss: 2.3718
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1932 - loss: 2.3715
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1932 - loss: 2.3713
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1933 - loss: 2.3712
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1933 - loss: 2.3710
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1933 - loss: 2.3709
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1934 - loss: 2.3707
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1935 - loss: 2.3706
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1935 - loss: 2.3705
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1935 - loss: 2.3704
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1936 - loss: 2.3704
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1936 - loss: 2.3703
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1936 - loss: 2.3702
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1936 - loss: 2.3701
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1937 - loss: 2.3700 
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1937 - loss: 2.3699
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 14ms/step - accuracy: 0.1942 - loss: 2.3621 - val_accuracy: 0.2026 - val_loss: 2.1281
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1937 - loss: 2.3697
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1938 - loss: 2.3696
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1938 - loss: 2.3694

Trial status: 17 TERMINATED | 3 RUNNING
Current time: 2025-10-31 15:17:11. Total running time: 12min 31s
Logical resource usage: 3.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23                                              │
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    RUNNING              2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27                                              │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24        1            607.522         0.187419 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25        1            692.143         0.219981 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29        1            632.987         0.372433 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29        1            562.331         0.177428 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18        1            590.703         0.203515 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21        1            677.558         0.306013 │
│ trial_8b084    TERMINATED           3   adam            relu                                   16                 16                  3                 1          0.000172735         21        1            744.741         0.39926  │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20        1            655.718         0.237558 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   16                 64                  3                 0          0.000176203         22        1            611.614         0.258094 │
│ trial_8b084    TERMINATED           3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28        1            706.591         0.20555  │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22        1            638.525         0.385014 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15        1            508.648         0.209991 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17        1            577.082         0.245513 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1938 - loss: 2.3691
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1939 - loss: 2.3689
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1939 - loss: 2.3687
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3685
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3683
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3682
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 9ms/step - accuracy: 0.2348 - loss: 2.2190 - val_accuracy: 0.2074 - val_loss: 2.2003
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3680
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3679
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3678
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3677
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 26/27
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3676
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3675
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 57ms/step - accuracy: 0.3125 - loss: 2.1873
[1m   8/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.3168 - loss: 2.0916   
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3674
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3673
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3672
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3671
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3670
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3670
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3669
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 8ms/step - accuracy: 0.3330 - loss: 1.8542[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3668
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1940 - loss: 2.3667
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1941 - loss: 2.3665
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1941 - loss: 2.3664
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1941 - loss: 2.3662
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1942 - loss: 2.3660
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1942 - loss: 2.3659
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1942 - loss: 2.3657
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1942 - loss: 2.3655
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1942 - loss: 2.3654
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1943 - loss: 2.3652
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1943 - loss: 2.3650
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1943 - loss: 2.3648
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1943 - loss: 2.3646
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1943 - loss: 2.3645
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1943 - loss: 2.3643
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1944 - loss: 2.3641
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1944 - loss: 2.3640
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1944 - loss: 2.3638
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1944 - loss: 2.3636
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1944 - loss: 2.3635
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1944 - loss: 2.3634
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1944 - loss: 2.3632
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 12ms/step - accuracy: 0.1945 - loss: 2.3630
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1945 - loss: 2.3629
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1945 - loss: 2.3628
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1945 - loss: 2.3627
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1945 - loss: 2.3625
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1946 - loss: 2.3624
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1946 - loss: 2.3623
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2512 - loss: 2.1774
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2509 - loss: 2.1780[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1946 - loss: 2.3622
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1946 - loss: 2.3621
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3620
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3619
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3618
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3617
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3617
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3616
[36m(train_cnn_ray_tune pid=1593438)[0m Epoch 23/23
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3615
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3615
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.3750 - loss: 1.5377
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.3817 - loss: 1.6915   
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3614
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3614
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3613
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3613
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3613
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3612
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3612
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3612
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3612
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3611
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3611
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3611
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3611
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3611
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3611
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3611
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3611
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3611
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3611
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3611
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3611
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3611
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3611
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3611
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3610
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3610
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3610
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3610
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3609
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3609
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3609
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3608
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3608
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 9ms/step - accuracy: 0.3330 - loss: 1.8531 - val_accuracy: 0.3463 - val_loss: 1.7478
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3608
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3607
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3607
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3606
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3606
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3606
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3605
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3605
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3605
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3605
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3604
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3604
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3604
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3604
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3604
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 8ms/step - accuracy: 0.3500 - loss: 1.7952[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3603
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1947 - loss: 2.3603
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3603
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3603
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3602
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3602
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3602
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3602
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3601
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3601
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3601
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3601
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3601
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3601
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3600
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3600
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3600
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3600
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1948 - loss: 2.3600
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3599
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3599
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3599
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3599
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3599
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3599
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3598
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3598
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3598
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m5s[0m 8ms/step - accuracy: 0.3446 - loss: 1.8112
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m5s[0m 8ms/step - accuracy: 0.3445 - loss: 1.8114[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3598
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3598
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3597
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3597
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3597
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3597
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3596
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3596
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3596
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3596
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3595
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3595
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3595
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3595
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3594
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3594
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3594
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3594
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3593
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3593
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3593
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3592
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3592
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3592
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3592
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3591
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3591
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step - accuracy: 0.1949 - loss: 2.3591
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 8ms/step - accuracy: 0.2405 - loss: 2.1975 - val_accuracy: 0.2109 - val_loss: 2.1991
[36m(train_cnn_ray_tune pid=1593443)[0m Epoch 27/27
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.3125 - loss: 2.1511
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 4ms/step - accuracy: 0.2394 - loss: 2.3199  
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 4ms/step - accuracy: 0.2431 - loss: 2.2619
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 13ms/step - accuracy: 0.1949 - loss: 2.3591 - val_accuracy: 0.1993 - val_loss: 2.1283
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   6/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.1738 - loss: 2.2986
[1m  11/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.1895 - loss: 2.3014
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  16/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.1879 - loss: 2.3225
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1863 - loss: 2.3342
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1850 - loss: 2.3396
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1845 - loss: 2.3426
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  36/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1836 - loss: 2.3446
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  41/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1824 - loss: 2.3442
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1821 - loss: 2.3432
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 8ms/step - accuracy: 0.2407 - loss: 2.1971[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1821 - loss: 2.3423
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1822 - loss: 2.3423
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1821 - loss: 2.3441
[1m  65/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1819 - loss: 2.3454
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1815 - loss: 2.3466
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1813 - loss: 2.3477
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1813 - loss: 2.3486
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1812 - loss: 2.3490
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  89/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1813 - loss: 2.3484
[1m  94/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.1816 - loss: 2.3476
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1818 - loss: 2.3470
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1821 - loss: 2.3467
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1824 - loss: 2.3461
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1827 - loss: 2.3455
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1829 - loss: 2.3448
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1832 - loss: 2.3440
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1834 - loss: 2.3432
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1836 - loss: 2.3424
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1838 - loss: 2.3419
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 144/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1840 - loss: 2.3415
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1841 - loss: 2.3412
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1843 - loss: 2.3410
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1845 - loss: 2.3409
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.1846 - loss: 2.3406
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1848 - loss: 2.3404
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1849 - loss: 2.3402
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1850 - loss: 2.3401
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1851 - loss: 2.3401
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 7ms/step - accuracy: 0.2344 - loss: 2.2054
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m5s[0m 7ms/step - accuracy: 0.2343 - loss: 2.2055[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1851 - loss: 2.3401
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1852 - loss: 2.3402
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1852 - loss: 2.3402
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1852 - loss: 2.3402
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1852 - loss: 2.3403
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1852 - loss: 2.3404
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1853 - loss: 2.3405
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1853 - loss: 2.3406
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1854 - loss: 2.3407
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.1855 - loss: 2.3407
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1855 - loss: 2.3408
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1856 - loss: 2.3409
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1856 - loss: 2.3410
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1857 - loss: 2.3412
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1858 - loss: 2.3413
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1858 - loss: 2.3415
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1859 - loss: 2.3417
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1859 - loss: 2.3420
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1859 - loss: 2.3424
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1859 - loss: 2.3427
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 334ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1859 - loss: 2.3430
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1860 - loss: 2.3433
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step   
[1m28/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1860 - loss: 2.3435
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m43/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1860 - loss: 2.3436
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.1860 - loss: 2.3438
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1861 - loss: 2.3439 
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1861 - loss: 2.3440
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1861 - loss: 2.3441
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1862 - loss: 2.3442
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1862 - loss: 2.3443
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1863 - loss: 2.3444
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1863 - loss: 2.3446
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1864 - loss: 2.3447
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1864 - loss: 2.3448
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1864 - loss: 2.3450
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 40ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1864 - loss: 2.3451
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3452
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 16/169[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step 
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 30/169[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m 46/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3453
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3455
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 62/169[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m 78/169[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3457
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3458
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m 92/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 4ms/step
[1m108/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3459
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3460
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m122/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 4ms/step
[1m138/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 9ms/step - accuracy: 0.3400 - loss: 1.8238 - val_accuracy: 0.3571 - val_loss: 1.7442
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 17/22
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.1250 - loss: 2.2670
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3461
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3462
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m152/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 3ms/step
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3463
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3464
[36m(train_cnn_ray_tune pid=1593438)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593438)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593438)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3465
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3466

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:17:27. Total running time: 12min 46s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             763.461 │
│ time_total_s                 763.461 │
│ training_iteration                 1 │
│ val_accuracy                 0.35708 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:17:27. Total running time: 12min 46s
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3467
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3468
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.1865 - loss: 2.3469
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 11ms/step - accuracy: 0.1865 - loss: 2.3471
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 11ms/step - accuracy: 0.1866 - loss: 2.3472
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 11ms/step - accuracy: 0.1866 - loss: 2.3473
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 11ms/step - accuracy: 0.1866 - loss: 2.3474
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1866 - loss: 2.3474
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1866 - loss: 2.3475
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1866 - loss: 2.3476
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1867 - loss: 2.3476
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1867 - loss: 2.3477
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1867 - loss: 2.3478
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1867 - loss: 2.3478
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m3s[0m 7ms/step - accuracy: 0.2342 - loss: 2.2058[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1868 - loss: 2.3479
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1868 - loss: 2.3479
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1868 - loss: 2.3479
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1869 - loss: 2.3479
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1869 - loss: 2.3479
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1870 - loss: 2.3479
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1870 - loss: 2.3479
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1871 - loss: 2.3479
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m7s[0m 11ms/step - accuracy: 0.1871 - loss: 2.3479
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1872 - loss: 2.3479
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1872 - loss: 2.3479
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1872 - loss: 2.3480
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1873 - loss: 2.3480
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1873 - loss: 2.3480
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1874 - loss: 2.3481
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1874 - loss: 2.3481
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1874 - loss: 2.3482
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1875 - loss: 2.3482
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1875 - loss: 2.3482
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1875 - loss: 2.3483
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1876 - loss: 2.3483
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1876 - loss: 2.3483
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1876 - loss: 2.3483
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1877 - loss: 2.3484
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1877 - loss: 2.3484
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 11ms/step - accuracy: 0.1877 - loss: 2.3484
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1877 - loss: 2.3485
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1878 - loss: 2.3485
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1878 - loss: 2.3485
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1878 - loss: 2.3485
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1879 - loss: 2.3486
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 7ms/step - accuracy: 0.2363 - loss: 2.2013
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 7ms/step - accuracy: 0.2363 - loss: 2.2012[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1879 - loss: 2.3486
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1879 - loss: 2.3486
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1880 - loss: 2.3486
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1880 - loss: 2.3486
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1880 - loss: 2.3486
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1881 - loss: 2.3486
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1881 - loss: 2.3486
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1881 - loss: 2.3486
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1881 - loss: 2.3486
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1882 - loss: 2.3487
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m5s[0m 11ms/step - accuracy: 0.1882 - loss: 2.3487
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1882 - loss: 2.3487
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1883 - loss: 2.3487
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1883 - loss: 2.3487
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1883 - loss: 2.3486
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1884 - loss: 2.3486
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1884 - loss: 2.3486
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1885 - loss: 2.3486
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1885 - loss: 2.3486
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1885 - loss: 2.3486
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1886 - loss: 2.3485
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1886 - loss: 2.3485
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1887 - loss: 2.3485
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1887 - loss: 2.3484
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1888 - loss: 2.3484
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.1888 - loss: 2.3484
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1889 - loss: 2.3483
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1889 - loss: 2.3483
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1890 - loss: 2.3482
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1890 - loss: 2.3482
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1890 - loss: 2.3481
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1891 - loss: 2.3481
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1891 - loss: 2.3480
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 8ms/step - accuracy: 0.2367 - loss: 2.2002 - val_accuracy: 0.2142 - val_loss: 2.1931
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1891 - loss: 2.3480
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1892 - loss: 2.3479
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1892 - loss: 2.3479
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1892 - loss: 2.3479
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1893 - loss: 2.3478
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1893 - loss: 2.3478
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1893 - loss: 2.3477
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 319ms/step
[1m17/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step   
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 11ms/step - accuracy: 0.1894 - loss: 2.3477
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1894 - loss: 2.3476
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m34/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1894 - loss: 2.3476
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1895 - loss: 2.3476
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1895 - loss: 2.3475
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 3ms/step
[1m85/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1895 - loss: 2.3475
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1895 - loss: 2.3475
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1896 - loss: 2.3474
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1896 - loss: 2.3474
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1896 - loss: 2.3473
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1896 - loss: 2.3473
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1896 - loss: 2.3473
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1897 - loss: 2.3472
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1897 - loss: 2.3472
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 32ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1897 - loss: 2.3471
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1897 - loss: 2.3471
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 17/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step 
[1m 34/169[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 11ms/step - accuracy: 0.1897 - loss: 2.3470
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1898 - loss: 2.3470
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[1m 69/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1898 - loss: 2.3469
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1898 - loss: 2.3469
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m 86/169[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 3ms/step
[1m104/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593443)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1898 - loss: 2.3468
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1898 - loss: 2.3468
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m122/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m140/169[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 7ms/step - accuracy: 0.2364 - loss: 2.2010[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1898 - loss: 2.3468
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1899 - loss: 2.3467
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m158/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 3ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1899 - loss: 2.3467
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1899 - loss: 2.3466

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:17:33. Total running time: 12min 52s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             769.734 │
│ time_total_s                 769.734 │
│ training_iteration                 1 │
│ val_accuracy                 0.21425 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:17:33. Total running time: 12min 52s
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1899 - loss: 2.3466
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1899 - loss: 2.3465
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1900 - loss: 2.3465
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.1900 - loss: 2.3464
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 11ms/step - accuracy: 0.1900 - loss: 2.3464
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 11ms/step - accuracy: 0.1900 - loss: 2.3464
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 11ms/step - accuracy: 0.1900 - loss: 2.3463
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step - accuracy: 0.1900 - loss: 2.3463
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step - accuracy: 0.1901 - loss: 2.3462
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step - accuracy: 0.1901 - loss: 2.3462
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step - accuracy: 0.1901 - loss: 2.3462
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step - accuracy: 0.1901 - loss: 2.3461
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 11ms/step - accuracy: 0.1901 - loss: 2.3461
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.1901 - loss: 2.3461
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.1902 - loss: 2.3460
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.1902 - loss: 2.3460
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.1902 - loss: 2.3460
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.1902 - loss: 2.3459
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.1902 - loss: 2.3459
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.1902 - loss: 2.3459
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.1903 - loss: 2.3458
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.1903 - loss: 2.3458
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.1903 - loss: 2.3458
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 11ms/step - accuracy: 0.1903 - loss: 2.3457 - val_accuracy: 0.2017 - val_loss: 2.1212
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 18/22
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1250 - loss: 2.4050
[36m(train_cnn_ray_tune pid=1593443)[0m 
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step - accuracy: 0.2366 - loss: 2.2004
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step - accuracy: 0.2367 - loss: 2.2003[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2179 - loss: 2.3081 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2242 - loss: 2.2600
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2150 - loss: 2.2464
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2116 - loss: 2.2359
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2104 - loss: 2.2322
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2093 - loss: 2.2303
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2074 - loss: 2.2357 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2001 - loss: 2.2684[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.1943 - loss: 2.3321
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.1943 - loss: 2.3322[32m [repeated 43x across cluster][0m

Trial status: 19 TERMINATED | 1 RUNNING
Current time: 2025-10-31 15:17:41. Total running time: 13min 1s
Logical resource usage: 1.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24        1            607.522         0.187419 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25        1            692.143         0.219981 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29        1            632.987         0.372433 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29        1            562.331         0.177428 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18        1            590.703         0.203515 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23        1            763.461         0.357077 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21        1            677.558         0.306013 │
│ trial_8b084    TERMINATED           3   adam            relu                                   16                 16                  3                 1          0.000172735         21        1            744.741         0.39926  │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20        1            655.718         0.237558 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   16                 64                  3                 0          0.000176203         22        1            611.614         0.258094 │
│ trial_8b084    TERMINATED           3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28        1            706.591         0.20555  │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22        1            638.525         0.385014 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27        1            769.734         0.214246 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15        1            508.648         0.209991 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17        1            577.082         0.245513 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.1958 - loss: 2.3297
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.1958 - loss: 2.3296[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.1958 - loss: 2.3296
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 9ms/step - accuracy: 0.1958 - loss: 2.3295 - val_accuracy: 0.2091 - val_loss: 2.1096
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 19/22
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 29ms/step - accuracy: 0.1250 - loss: 2.1885
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2122 - loss: 2.1913  
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2149 - loss: 2.2828
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2148 - loss: 2.2831[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2102 - loss: 2.2919
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2102 - loss: 2.2919[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2100 - loss: 2.2921
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2099 - loss: 2.2921
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2099 - loss: 2.2922
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2098 - loss: 2.2923
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2097 - loss: 2.2924
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 9ms/step - accuracy: 0.2097 - loss: 2.2924 - val_accuracy: 0.2041 - val_loss: 2.1047
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 20/22
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.0625 - loss: 2.6403
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.1514 - loss: 2.4991 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.1752 - loss: 2.4419
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.1812 - loss: 2.4106
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.1870 - loss: 2.3876
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1905 - loss: 2.3716 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1929 - loss: 2.3618
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1982 - loss: 2.3381
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  61/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1989 - loss: 2.3342
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  67/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1996 - loss: 2.3308
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1999 - loss: 2.3282
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1999 - loss: 2.3258
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1997 - loss: 2.3234
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  91/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1995 - loss: 2.3210
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1994 - loss: 2.3181
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2006 - loss: 2.2900
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2006 - loss: 2.2898[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2026 - loss: 2.2895
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2027 - loss: 2.2895[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 9ms/step - accuracy: 0.2033 - loss: 2.2900 - val_accuracy: 0.2204 - val_loss: 2.0868
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 21/22
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1875 - loss: 2.1029
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1890 - loss: 2.3041  
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1828 - loss: 2.3067
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2033 - loss: 2.2834
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2034 - loss: 2.2836[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2038 - loss: 2.2849
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2038 - loss: 2.2850
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2039 - loss: 2.2852
Trial status: 19 TERMINATED | 1 RUNNING
Current time: 2025-10-31 15:18:11. Total running time: 13min 31s
Logical resource usage: 1.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22                                              │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24        1            607.522         0.187419 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25        1            692.143         0.219981 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29        1            632.987         0.372433 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29        1            562.331         0.177428 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18        1            590.703         0.203515 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23        1            763.461         0.357077 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21        1            677.558         0.306013 │
│ trial_8b084    TERMINATED           3   adam            relu                                   16                 16                  3                 1          0.000172735         21        1            744.741         0.39926  │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20        1            655.718         0.237558 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   16                 64                  3                 0          0.000176203         22        1            611.614         0.258094 │
│ trial_8b084    TERMINATED           3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28        1            706.591         0.20555  │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22        1            638.525         0.385014 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27        1            769.734         0.214246 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15        1            508.648         0.209991 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17        1            577.082         0.245513 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2061 - loss: 2.2857
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2061 - loss: 2.2857[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2066 - loss: 2.2852
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2067 - loss: 2.2852
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2067 - loss: 2.2852
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2067 - loss: 2.2851
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2067 - loss: 2.2851
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 9ms/step - accuracy: 0.2069 - loss: 2.2843 - val_accuracy: 0.2157 - val_loss: 2.0767
[36m(train_cnn_ray_tune pid=1593432)[0m Epoch 22/22
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.4375 - loss: 1.6674
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m   7/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.3417 - loss: 2.0239 
[1m  13/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2905 - loss: 2.1348
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2687 - loss: 2.1753
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2550 - loss: 2.1929
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  31/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2478 - loss: 2.1987
[1m  37/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2434 - loss: 2.2084
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2409 - loss: 2.2143
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2381 - loss: 2.2182 
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2179 - loss: 2.2395
[1m 170/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.2179 - loss: 2.2391[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2180 - loss: 2.2411
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2178 - loss: 2.2416
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2178 - loss: 2.2418
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2178 - loss: 2.2419
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m6s[0m 9ms/step - accuracy: 0.2177 - loss: 2.2421
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2157 - loss: 2.2485
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2157 - loss: 2.2486[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2147 - loss: 2.2515
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2147 - loss: 2.2515
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2147 - loss: 2.2516
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 9ms/step - accuracy: 0.2147 - loss: 2.2516
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2147 - loss: 2.2516
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2146 - loss: 2.2517
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2146 - loss: 2.2517
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2146 - loss: 2.2517
2025-10-31 15:18:31,092	INFO tune.py:1009 -- Wrote the latest version of all result files and experiment state to '/mnt/nvme1n2/git/uniovi-simur-wearablepermed-data/output/Paper_results/cases_dataset_C/case_C_CAPTURE24_acc_gyr_17_classes/CAPTURE24_hyperparameters_tuning' in 0.0083s.
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2146 - loss: 2.2518
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2145 - loss: 2.2519
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2145 - loss: 2.2520
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2144 - loss: 2.2520
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2144 - loss: 2.2521
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2144 - loss: 2.2521
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2144 - loss: 2.2522
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2144 - loss: 2.2522
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2144 - loss: 2.2522
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 9ms/step - accuracy: 0.2144 - loss: 2.2522 - val_accuracy: 0.2272 - val_loss: 2.0662
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 159ms/step
[1m23/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step   
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2145 - loss: 2.2519
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2145 - loss: 2.2520[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 23/169[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step 
[1m 48/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m 73/169[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step
[1m 98/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m123/169[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m148/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=1593432)[0m 
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step

Trial trial_8b084 finished iteration 1 at 2025-10-31 15:18:31. Total running time: 13min 50s
╭──────────────────────────────────────╮
│ Trial trial_8b084 result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             827.609 │
│ time_total_s                 827.609 │
│ training_iteration                 1 │
│ val_accuracy                  0.2272 │
╰──────────────────────────────────────╯

Trial trial_8b084 completed after 1 iterations at 2025-10-31 15:18:31. Total running time: 13min 50s

Trial status: 20 TERMINATED
Current time: 2025-10-31 15:18:31. Total running time: 13min 50s
Logical resource usage: 1.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
I0000 00:00:1761920311.220198 1591802 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
[36m(train_cnn_ray_tune pid=1593432)[0m /home/simur/git/uniovi-simur-wearablepermed-ml/.venv/lib/python3.12/site-packages/ray/train/_internal/session.py:772: RayDeprecationWarning: `ray.train.report` should be switched to `ray.tune.report` when running in a function passed to Ray Tune. This will be an error in the future. See this issue for more context: https://github.com/ray-project/ray/issues/49454
[36m(train_cnn_ray_tune pid=1593432)[0m   _log_deprecation_warning(
╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Trial name     status         N_capas   optimizador     funcion_activacion       tamanho_minilote     numero_filtros     tamanho_filtro     num_resblocks     tasa_aprendizaje     epochs     iter     total time (s)     val_accuracy │
├────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  5                 0          8.35984e-06         24        1            607.522         0.187419 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 16                  3                 0          6.69281e-05         25        1            692.143         0.219981 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 0          0.000165493         29        1            632.987         0.372433 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 16                  3                 1          3.60109e-05         29        1            562.331         0.177428 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 16                  3                 0          3.95407e-05         18        1            590.703         0.203515 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   32                 64                  5                 1          0.000113216         29        1            461.048         0.376688 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 32                  5                 0          0.000160518         25        1            440.267         0.365957 │
│ trial_8b084    TERMINATED           2   adam            relu                                   16                 64                  3                 0          3.44013e-05         23        1            763.461         0.357077 │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   32                 64                  3                 0          1.01509e-05         21        1            677.558         0.306013 │
│ trial_8b084    TERMINATED           3   adam            relu                                   16                 16                  3                 1          0.000172735         21        1            744.741         0.39926  │
│ trial_8b084    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          1.97975e-05         16        1            434.114         0.192044 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          2.54835e-05         20        1            655.718         0.237558 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   16                 64                  3                 0          0.000176203         22        1            611.614         0.258094 │
│ trial_8b084    TERMINATED           3   adam            relu                                   32                 32                  5                 1          7.97935e-06         28        1            706.591         0.20555  │
│ trial_8b084    TERMINATED           3   rmsprop         relu                                   16                 32                  5                 0          0.000182484         22        1            638.525         0.385014 │
│ trial_8b084    TERMINATED           3   adam            relu                                   16                 64                  5                 1          6.88428e-06         22        1            827.609         0.227197 │
│ trial_8b084    TERMINATED           3   adam            tanh                                   32                 64                  3                 1          6.77773e-05         23        1            477.259         0.253099 │
│ trial_8b084    TERMINATED           2   adam            tanh                                   16                 32                  5                 1          3.24118e-05         27        1            769.734         0.214246 │
│ trial_8b084    TERMINATED           2   rmsprop         relu                                   16                 16                  3                 0          3.54337e-05         15        1            508.648         0.209991 │
│ trial_8b084    TERMINATED           2   rmsprop         tanh                                   16                 64                  3                 0          0.00012443          17        1            577.082         0.245513 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Mejores hiperparámetros: {'N_capas': 3, 'optimizador': 'adam', 'funcion_activacion': 'relu', 'tamanho_minilote': 16, 'numero_filtros': 16, 'tamanho_filtro': 3, 'num_resblocks': 1, 'tasa_aprendizaje': 0.00017273459255468389, 'epochs': 21}
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761920314.348028 1639258 service.cc:152] XLA service 0x7c6fdc01e520 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761920314.348089 1639258 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:18:34.420820: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761920314.844684 1639258 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761920317.556944 1639258 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:48:35[0m 6s/step - accuracy: 0.1875 - loss: 3.0698
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.0862 - loss: 3.3388    
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0800 - loss: 3.3389
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0797 - loss: 3.3253
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0797 - loss: 3.3079
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0791 - loss: 3.2909
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0790 - loss: 3.2757
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0793 - loss: 3.2630
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0798 - loss: 3.2512
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0803 - loss: 3.2401
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0810 - loss: 3.2286
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0815 - loss: 3.2180
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0823 - loss: 3.2076
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0829 - loss: 3.1976
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0837 - loss: 3.1874
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0844 - loss: 3.1778
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0853 - loss: 3.1685
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0862 - loss: 3.1591
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0870 - loss: 3.1509
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0877 - loss: 3.1428
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0883 - loss: 3.1353
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0890 - loss: 3.1276
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0897 - loss: 3.1206
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0903 - loss: 3.1133
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0908 - loss: 3.1067
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0913 - loss: 3.1002
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0918 - loss: 3.0936
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0922 - loss: 3.0876
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0926 - loss: 3.0818
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0930 - loss: 3.0755
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0934 - loss: 3.0697
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0939 - loss: 3.0634
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0943 - loss: 3.0571
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0947 - loss: 3.0515
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0950 - loss: 3.0466
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0954 - loss: 3.0414
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0958 - loss: 3.0357
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0962 - loss: 3.0304
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0966 - loss: 3.0255
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0970 - loss: 3.0206
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0973 - loss: 3.0160
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0977 - loss: 3.0112
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0980 - loss: 3.0066
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0984 - loss: 3.0021
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.0987 - loss: 2.9982
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.0987 - loss: 2.9981 - val_accuracy: 0.1367 - val_loss: 2.3855
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.4650
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1604 - loss: 2.5055  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1551 - loss: 2.5235
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1533 - loss: 2.5272
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1529 - loss: 2.5295
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1519 - loss: 2.5321
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1507 - loss: 2.5355
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1496 - loss: 2.5370
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1488 - loss: 2.5379
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1482 - loss: 2.5389
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1478 - loss: 2.5396
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1474 - loss: 2.5402
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1473 - loss: 2.5400
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1472 - loss: 2.5396
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1471 - loss: 2.5393
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1470 - loss: 2.5392
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1468 - loss: 2.5389
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1467 - loss: 2.5386
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1465 - loss: 2.5381
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1463 - loss: 2.5376
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1462 - loss: 2.5369
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1462 - loss: 2.5362
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1461 - loss: 2.5355
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1461 - loss: 2.5349
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1460 - loss: 2.5342
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.5337
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.5330
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.5323
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.5317
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.5309
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.5303
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.5296
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.5290
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.5283
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1461 - loss: 2.5276
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1461 - loss: 2.5269
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1461 - loss: 2.5262
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1462 - loss: 2.5255
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1462 - loss: 2.5247
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1463 - loss: 2.5239
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1463 - loss: 2.5231
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1464 - loss: 2.5223
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1464 - loss: 2.5215
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1465 - loss: 2.5205
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1466 - loss: 2.5196
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1466 - loss: 2.5191 - val_accuracy: 0.1878 - val_loss: 2.2284
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.1250 - loss: 2.1234
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1922 - loss: 2.2744  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1877 - loss: 2.3088
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1814 - loss: 2.3270
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1773 - loss: 2.3377
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1742 - loss: 2.3463
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1720 - loss: 2.3507
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3538
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1707 - loss: 2.3558
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1704 - loss: 2.3582
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1700 - loss: 2.3606
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1698 - loss: 2.3622
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1696 - loss: 2.3628
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1695 - loss: 2.3630
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1693 - loss: 2.3630
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1691 - loss: 2.3630
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1690 - loss: 2.3628
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1688 - loss: 2.3625
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1686 - loss: 2.3624
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3624
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1683 - loss: 2.3623
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1682 - loss: 2.3623
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3620
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3618
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1679 - loss: 2.3616
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1678 - loss: 2.3615
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1677 - loss: 2.3614
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1676 - loss: 2.3612
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1675 - loss: 2.3611
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1674 - loss: 2.3610
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1673 - loss: 2.3608
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1672 - loss: 2.3607
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1671 - loss: 2.3605
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1670 - loss: 2.3603
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1669 - loss: 2.3601
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1669 - loss: 2.3599
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3597
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3595
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3593
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3590
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3587
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3584
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3581
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3578
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3576
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3573
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3573 - val_accuracy: 0.2054 - val_loss: 2.1443
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.4658
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1637 - loss: 2.3355  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1654 - loss: 2.3241
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1653 - loss: 2.3234
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1663 - loss: 2.3213
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1678 - loss: 2.3190
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1685 - loss: 2.3163
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1694 - loss: 2.3130
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1697 - loss: 2.3106
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1701 - loss: 2.3085
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1705 - loss: 2.3066
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3052
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3038
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3024
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1722 - loss: 2.3012
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1726 - loss: 2.3003
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1728 - loss: 2.2995
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1730 - loss: 2.2988
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1731 - loss: 2.2981
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1732 - loss: 2.2975
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1733 - loss: 2.2969
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.2962
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1735 - loss: 2.2956
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1737 - loss: 2.2949
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1740 - loss: 2.2942
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1741 - loss: 2.2936
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1743 - loss: 2.2930
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1744 - loss: 2.2924
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1746 - loss: 2.2918
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1748 - loss: 2.2912
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1750 - loss: 2.2907
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1752 - loss: 2.2901
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1754 - loss: 2.2896
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1755 - loss: 2.2892
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1757 - loss: 2.2887
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1758 - loss: 2.2884
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2879
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1761 - loss: 2.2875
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1762 - loss: 2.2871
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1763 - loss: 2.2868
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1763 - loss: 2.2864
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1765 - loss: 2.2860
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1766 - loss: 2.2856
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1767 - loss: 2.2852
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1768 - loss: 2.2848
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1770 - loss: 2.2843
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1771 - loss: 2.2841 - val_accuracy: 0.2048 - val_loss: 2.1082
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1875 - loss: 2.4646
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2057 - loss: 2.3798  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2086 - loss: 2.3104
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2099 - loss: 2.2777
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2101 - loss: 2.2609
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2079 - loss: 2.2529
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2069 - loss: 2.2482
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2063 - loss: 2.2443
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2055 - loss: 2.2414
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2054 - loss: 2.2382
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2052 - loss: 2.2358
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2052 - loss: 2.2331
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2052 - loss: 2.2310
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2051 - loss: 2.2298
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2052 - loss: 2.2287
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2054 - loss: 2.2276
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2055 - loss: 2.2266
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2057 - loss: 2.2258
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2058 - loss: 2.2250
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2059 - loss: 2.2243
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2060 - loss: 2.2235
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2062 - loss: 2.2226
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2063 - loss: 2.2220
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2063 - loss: 2.2214
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2064 - loss: 2.2208
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.2202
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.2197
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.2191
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.2186
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.2181
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.2176
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.2172
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2065 - loss: 2.2168
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2066 - loss: 2.2164
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2066 - loss: 2.2160
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2067 - loss: 2.2156
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2067 - loss: 2.2153
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2068 - loss: 2.2149
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2069 - loss: 2.2146
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2069 - loss: 2.2143
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2070 - loss: 2.2140
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2071 - loss: 2.2137
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2071 - loss: 2.2134
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2072 - loss: 2.2131
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2073 - loss: 2.2127
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2073 - loss: 2.2126 - val_accuracy: 0.2977 - val_loss: 2.0155
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9255
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2354 - loss: 2.1228  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2361 - loss: 2.1275
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2355 - loss: 2.1276
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2352 - loss: 2.1294
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2353 - loss: 2.1289
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2352 - loss: 2.1289
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2340 - loss: 2.1304
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2324 - loss: 2.1328
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2313 - loss: 2.1354
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2302 - loss: 2.1379
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2294 - loss: 2.1401
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2290 - loss: 2.1415
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2285 - loss: 2.1429
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.1445
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2276 - loss: 2.1460
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2273 - loss: 2.1473
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2270 - loss: 2.1487
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2267 - loss: 2.1496
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2265 - loss: 2.1504
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2264 - loss: 2.1509
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2264 - loss: 2.1513
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2264 - loss: 2.1515
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2265 - loss: 2.1516
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.1515
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2267 - loss: 2.1514
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2267 - loss: 2.1512
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2268 - loss: 2.1511
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2268 - loss: 2.1510
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2269 - loss: 2.1508
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2270 - loss: 2.1505
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2271 - loss: 2.1503
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2272 - loss: 2.1499
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2273 - loss: 2.1496
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2275 - loss: 2.1492
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2276 - loss: 2.1488
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2278 - loss: 2.1484
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2279 - loss: 2.1481
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2280 - loss: 2.1479
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2281 - loss: 2.1476
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2283 - loss: 2.1473
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2284 - loss: 2.1471
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2285 - loss: 2.1468
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2286 - loss: 2.1465
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.1462
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2288 - loss: 2.1461 - val_accuracy: 0.2851 - val_loss: 1.9664
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.0834
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1975 - loss: 2.1704  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2070 - loss: 2.1424
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2169 - loss: 2.1190
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2215 - loss: 2.1075
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2254 - loss: 2.1018
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2292 - loss: 2.0977
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2321 - loss: 2.0947
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2342 - loss: 2.0928
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2357 - loss: 2.0919
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.0911
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2387 - loss: 2.0901
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2399 - loss: 2.0893
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2411 - loss: 2.0884
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.0880
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.0879
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.0877
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2434 - loss: 2.0874
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2438 - loss: 2.0874
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2441 - loss: 2.0873
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2445 - loss: 2.0872
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2448 - loss: 2.0870
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2452 - loss: 2.0869
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2455 - loss: 2.0868
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2458 - loss: 2.0866
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.0865
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2463 - loss: 2.0862
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.0859
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.0857
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.0855
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.0853
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2473 - loss: 2.0851
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2475 - loss: 2.0849
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2477 - loss: 2.0847
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2479 - loss: 2.0845
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2481 - loss: 2.0843
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2483 - loss: 2.0841
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.0838
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.0835
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2490 - loss: 2.0832
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2491 - loss: 2.0829
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2493 - loss: 2.0827
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2495 - loss: 2.0824
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2497 - loss: 2.0821
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2499 - loss: 2.0818
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2499 - loss: 2.0817 - val_accuracy: 0.2979 - val_loss: 1.9181
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.6570
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9470  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2743 - loss: 1.9783
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2671 - loss: 1.9945
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2645 - loss: 2.0034
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0060
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0087
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2652 - loss: 2.0095
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2665 - loss: 2.0095
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2674 - loss: 2.0095
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2678 - loss: 2.0099
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2682 - loss: 2.0101
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.0098
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2690 - loss: 2.0094
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2694 - loss: 2.0090
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.0088
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2698 - loss: 2.0085
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2701 - loss: 2.0082
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.0080
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0080
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2708 - loss: 2.0081
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0083
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2712 - loss: 2.0085
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0088
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.0091
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0094
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2716 - loss: 2.0096
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0098
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.0101
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0103
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0105
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0106
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0107
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0108
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0110
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0112
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0114
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0116
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0117
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0118
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0120
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0121
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2721 - loss: 2.0122
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2721 - loss: 2.0123
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0125
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0126 - val_accuracy: 0.3206 - val_loss: 1.8761
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9099
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3007 - loss: 1.8680  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2918 - loss: 1.8938
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2903 - loss: 1.9086
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2902 - loss: 1.9149
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2916 - loss: 1.9187
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 1.9216
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 1.9251
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 1.9278
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2948 - loss: 1.9311
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9331
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 1.9351
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9365
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9379
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9391
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 1.9402
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 1.9414
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 1.9426
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 1.9437
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 1.9449
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 1.9458
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9466
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2971 - loss: 1.9476
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 1.9483
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9491
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 1.9497
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9503
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9509
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9515
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9521
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2961 - loss: 1.9527
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9532
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9537
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 1.9542
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 1.9546
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 1.9549
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2958 - loss: 1.9552
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2957 - loss: 1.9555
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2957 - loss: 1.9558
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9560
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9563
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 1.9565
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 1.9567
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9570
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9572
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9574 - val_accuracy: 0.3297 - val_loss: 1.8278
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.0678
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2343 - loss: 2.0478  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2447 - loss: 2.0276
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2539 - loss: 2.0185
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2589 - loss: 2.0102
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2635 - loss: 2.0002
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2665 - loss: 1.9930
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 1.9889
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 1.9862
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2720 - loss: 1.9835
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2736 - loss: 1.9815
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2748 - loss: 1.9799
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 1.9787
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 1.9773
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 1.9757
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 1.9740
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 1.9721
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 1.9706
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9693
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 1.9682
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2824 - loss: 1.9673
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9665
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 1.9656
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 1.9646
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 1.9635
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 1.9626
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 1.9619
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 1.9614
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2864 - loss: 1.9606
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 1.9599
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2872 - loss: 1.9592
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 1.9585
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2879 - loss: 1.9580
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2881 - loss: 1.9575
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2884 - loss: 1.9570
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2887 - loss: 1.9565
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2889 - loss: 1.9561
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2891 - loss: 1.9557
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 1.9553
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2895 - loss: 1.9550
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2897 - loss: 1.9547
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2899 - loss: 1.9544
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2901 - loss: 1.9540
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2903 - loss: 1.9537
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2905 - loss: 1.9533
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2906 - loss: 1.9531 - val_accuracy: 0.3338 - val_loss: 1.8157
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.5229
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2840 - loss: 1.8576  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2892 - loss: 1.8561
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2967 - loss: 1.8522
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3022 - loss: 1.8491
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3051 - loss: 1.8491
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3061 - loss: 1.8505
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8540
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 1.8570
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 1.8596
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 1.8632
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 1.8670
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 1.8705
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3054 - loss: 1.8732
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 1.8753
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 1.8771
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 1.8786
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 1.8797
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 1.8810
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 1.8824
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 1.8836
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 1.8845
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 1.8853
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 1.8860
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 1.8866
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 1.8871
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.8876
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.8881
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.8885
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.8891
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.8895
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.8900
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.8904
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.8907
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.8910
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.8913
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8915
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8917
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8919
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8921
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8923
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8924
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8926
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8928
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8930
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8931 - val_accuracy: 0.3704 - val_loss: 1.7973
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.2500 - loss: 1.8128
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8956  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8857
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8889
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3275 - loss: 1.8888
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8882
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3254 - loss: 1.8912
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 1.8934
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8930
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 1.8920
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8910
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 1.8905
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8902
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8900
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8894
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 1.8884
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 1.8876
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8872
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8869
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8867
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 1.8865
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 1.8860
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8855
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8849
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 1.8843
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8838
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3242 - loss: 1.8834
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8830
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8826
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 1.8823
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 1.8820
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 1.8817
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 1.8815
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 1.8812
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 1.8810
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 1.8807
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 1.8805
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 1.8802
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 1.8800
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 1.8798
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 1.8795
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 1.8793
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 1.8792
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3228 - loss: 1.8790
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 1.8788
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3227 - loss: 1.8788 - val_accuracy: 0.3480 - val_loss: 1.7851
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.6450
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3198 - loss: 1.8525  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8758
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8832
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 1.8813
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3220 - loss: 1.8777
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3230 - loss: 1.8752
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3233 - loss: 1.8744
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3238 - loss: 1.8729
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 1.8710
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 1.8698
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 1.8687
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3256 - loss: 1.8673
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8656
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3261 - loss: 1.8642
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8629
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8624
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 1.8618
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 1.8612
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3271 - loss: 1.8607
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3273 - loss: 1.8602
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3276 - loss: 1.8596
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3279 - loss: 1.8589
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3282 - loss: 1.8582
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8577
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3286 - loss: 1.8573
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8568
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3289 - loss: 1.8564
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3291 - loss: 1.8560
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3293 - loss: 1.8555
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8551
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3296 - loss: 1.8547
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3298 - loss: 1.8544
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 1.8541
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8539
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 1.8535
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8531
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 1.8527
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3309 - loss: 1.8523
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 1.8519
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8516
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8513
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3314 - loss: 1.8510
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8507
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8504
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8502 - val_accuracy: 0.3389 - val_loss: 1.7945
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.5000 - loss: 1.6768
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3685 - loss: 1.8373  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3615 - loss: 1.8435
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3564 - loss: 1.8414
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3521 - loss: 1.8391
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3493 - loss: 1.8376
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3481 - loss: 1.8349
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3472 - loss: 1.8314
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.8286
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3457 - loss: 1.8268
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3450 - loss: 1.8260
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3445 - loss: 1.8252
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3441 - loss: 1.8238
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3438 - loss: 1.8227
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3434 - loss: 1.8221
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3431 - loss: 1.8219
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3429 - loss: 1.8217
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8215
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8213
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8211
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8209
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8208
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8206
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8203
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8200
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8199
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8197
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8196
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8195
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8195
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8194
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8194
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3424 - loss: 1.8193
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3424 - loss: 1.8192
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8191
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8190
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8188
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8187
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8186
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8185
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8184
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8183
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8181
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8179
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8178
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8177 - val_accuracy: 0.3748 - val_loss: 1.8122
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.3750 - loss: 1.7887
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3247 - loss: 1.7917  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3301 - loss: 1.7910
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3384 - loss: 1.7780
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3426 - loss: 1.7726
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7696
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3478 - loss: 1.7671
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7650
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7629
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7614
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7609
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7609
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7611
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3556 - loss: 1.7613
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7614
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7618
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7623
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7626
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7629
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7633
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7637
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7641
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7646
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7651
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7656
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7659
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3559 - loss: 1.7662
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7666
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7670
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3557 - loss: 1.7673
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3556 - loss: 1.7676
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3555 - loss: 1.7680
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7683
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3553 - loss: 1.7687
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7692
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3551 - loss: 1.7695
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7699
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7702
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7705
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7708
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7710
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7713
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7715
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7717
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7719
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7721 - val_accuracy: 0.3445 - val_loss: 1.8053
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 26ms/step - accuracy: 0.1875 - loss: 1.9448
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2879 - loss: 1.8733  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3153 - loss: 1.8176
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3263 - loss: 1.7942
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3320 - loss: 1.7834
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3356 - loss: 1.7775
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3387 - loss: 1.7719
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7682
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3430 - loss: 1.7649
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3449 - loss: 1.7615
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3464 - loss: 1.7588
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3475 - loss: 1.7568
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3481 - loss: 1.7563
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3486 - loss: 1.7557
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.7552
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7549
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7550
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3503 - loss: 1.7553
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3506 - loss: 1.7557
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7559
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7561
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3514 - loss: 1.7566
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7572
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7578
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7585
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3516 - loss: 1.7591
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3517 - loss: 1.7596
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7599
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7603
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7607
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3522 - loss: 1.7609
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7612
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7614
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7616
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3525 - loss: 1.7618
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7620
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7621
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7622
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3527 - loss: 1.7624
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3527 - loss: 1.7625
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3528 - loss: 1.7626
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3528 - loss: 1.7627
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7629
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7630
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3530 - loss: 1.7631
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3530 - loss: 1.7631
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3530 - loss: 1.7631 - val_accuracy: 0.3648 - val_loss: 1.7800
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.4352
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3346 - loss: 1.8665  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8467
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3350 - loss: 1.8435
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8324
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3432 - loss: 1.8215
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3458 - loss: 1.8106
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.8013
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3488 - loss: 1.7949
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3501 - loss: 1.7894
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3508 - loss: 1.7852
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3513 - loss: 1.7822
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3517 - loss: 1.7794
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3521 - loss: 1.7767
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3525 - loss: 1.7743
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7725
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7708
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7693
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7677
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7661
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3551 - loss: 1.7647
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7635
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7624
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7614
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7605
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7595
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7586
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7579
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7571
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7565
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7558
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7551
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7545
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7539
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7534
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7529
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7524
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7520
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7517
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7513
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7509
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7506
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7502
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7499
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7496
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7494 - val_accuracy: 0.3748 - val_loss: 1.7719
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.3125 - loss: 1.8373
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7957  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3812 - loss: 1.7669
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3780 - loss: 1.7639
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7616
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3754 - loss: 1.7585
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3744 - loss: 1.7549
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7519
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3747 - loss: 1.7493
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7463
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7438
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7420
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3748 - loss: 1.7410
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3744 - loss: 1.7409
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3739 - loss: 1.7411
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7414
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3732 - loss: 1.7416
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7416
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7416
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7415
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7416
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3726 - loss: 1.7417
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7417
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7417
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7418
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3720 - loss: 1.7418
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7418
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7417
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7414
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7410
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7407
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7403
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7400
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7395
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7391
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7387
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7382
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7377
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7373
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7369
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7367
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7364
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7362
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7360
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7357
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7357 - val_accuracy: 0.3824 - val_loss: 1.7788
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.3185
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4222 - loss: 1.6040  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4046 - loss: 1.6426
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3987 - loss: 1.6525
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6605
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6646
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6700
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3910 - loss: 1.6745
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3901 - loss: 1.6785
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3894 - loss: 1.6815
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3890 - loss: 1.6831
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3887 - loss: 1.6841
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3885 - loss: 1.6847
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3883 - loss: 1.6849
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3880 - loss: 1.6856
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3878 - loss: 1.6862
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3877 - loss: 1.6866
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3875 - loss: 1.6871
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3874 - loss: 1.6875
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3871 - loss: 1.6879
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6884
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6888
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6893
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3863 - loss: 1.6897
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3862 - loss: 1.6900
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3861 - loss: 1.6903
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6905
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6906
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6907
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6908
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3858 - loss: 1.6909
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3858 - loss: 1.6910
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3857 - loss: 1.6911
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3856 - loss: 1.6912
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.6914
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3853 - loss: 1.6916
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3852 - loss: 1.6918
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3851 - loss: 1.6920
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6922
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3848 - loss: 1.6924
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6927
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6929
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3844 - loss: 1.6931
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6933
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6935
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6935 - val_accuracy: 0.3869 - val_loss: 1.7733
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7847
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4167 - loss: 1.6292  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4047 - loss: 1.6310
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3994 - loss: 1.6300
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6337
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3924 - loss: 1.6382
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3898 - loss: 1.6438
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6502
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3871 - loss: 1.6555
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6591
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3868 - loss: 1.6617
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6635
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3862 - loss: 1.6646
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6655
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3856 - loss: 1.6662
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3854 - loss: 1.6670
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6681
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6690
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6697
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3841 - loss: 1.6702
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3839 - loss: 1.6707
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3838 - loss: 1.6713
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6719
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6726
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3831 - loss: 1.6731
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6736
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3829 - loss: 1.6740
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3828 - loss: 1.6743
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3827 - loss: 1.6745
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3827 - loss: 1.6747
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3827 - loss: 1.6749
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6750
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6751
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6752
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6753
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6754
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6754
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6754
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6754
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6753
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6753
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6753
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6753
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6753
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6753 - val_accuracy: 0.3758 - val_loss: 1.7869
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.5625 - loss: 1.9225
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4622 - loss: 1.6538  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4429 - loss: 1.6452
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4347 - loss: 1.6439
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4266 - loss: 1.6465
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4210 - loss: 1.6478
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4172 - loss: 1.6504
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4147 - loss: 1.6521
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4122 - loss: 1.6547
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4105 - loss: 1.6556
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4092 - loss: 1.6566
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4081 - loss: 1.6575
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4071 - loss: 1.6578
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4064 - loss: 1.6579
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4058 - loss: 1.6579
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4053 - loss: 1.6578
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4049 - loss: 1.6574
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4047 - loss: 1.6569
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4043 - loss: 1.6567
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4041 - loss: 1.6564
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4039 - loss: 1.6560
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4036 - loss: 1.6557
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4033 - loss: 1.6554
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4031 - loss: 1.6551
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4029 - loss: 1.6549
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4027 - loss: 1.6548
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4025 - loss: 1.6547
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4023 - loss: 1.6547
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4021 - loss: 1.6547
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4019 - loss: 1.6547
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4017 - loss: 1.6546
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4016 - loss: 1.6545
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4014 - loss: 1.6544
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4012 - loss: 1.6544
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6543
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4010 - loss: 1.6543
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4008 - loss: 1.6542
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4006 - loss: 1.6542
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4005 - loss: 1.6541
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4003 - loss: 1.6540
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4002 - loss: 1.6540
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4000 - loss: 1.6540
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3999 - loss: 1.6540
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3998 - loss: 1.6540
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3997 - loss: 1.6540
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3996 - loss: 1.6540 - val_accuracy: 0.3795 - val_loss: 1.7903

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 1s/step
[1m43/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:19:41.997727: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
2025-10-31 15:19:57.336804: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:19:57.348126: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761920397.361207 1642632 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761920397.365451 1642632 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761920397.375277 1642632 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920397.375297 1642632 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920397.375300 1642632 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920397.375302 1642632 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:19:57.378533: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761920399.745796 1642632 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761920402.862134 1642731 service.cc:152] XLA service 0x766a74003040 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761920402.862186 1642731 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:20:02.925445: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761920403.345373 1642731 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761920406.016416 1642731 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:16[0m 6s/step - accuracy: 0.0625 - loss: 3.6687
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.0884 - loss: 3.2047    
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0841 - loss: 3.2129
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0902 - loss: 3.1942
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0936 - loss: 3.1796
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0949 - loss: 3.1650
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0956 - loss: 3.1540
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0965 - loss: 3.1411
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0973 - loss: 3.1300
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0980 - loss: 3.1196
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0990 - loss: 3.1087
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0999 - loss: 3.0992
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1006 - loss: 3.0908
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1014 - loss: 3.0818
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1022 - loss: 3.0734
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1029 - loss: 3.0649
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1036 - loss: 3.0573
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1043 - loss: 3.0497
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1049 - loss: 3.0424
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1056 - loss: 3.0350
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1061 - loss: 3.0290
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1067 - loss: 3.0224
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1074 - loss: 3.0160
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1079 - loss: 3.0100
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1084 - loss: 3.0040
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1089 - loss: 2.9984
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1093 - loss: 2.9928
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1098 - loss: 2.9873
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1102 - loss: 2.9813
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1106 - loss: 2.9766
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1110 - loss: 2.9709
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1115 - loss: 2.9654
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1119 - loss: 2.9599
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1122 - loss: 2.9551
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1126 - loss: 2.9505
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1129 - loss: 2.9457
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1133 - loss: 2.9408
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1136 - loss: 2.9363
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1139 - loss: 2.9318
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1142 - loss: 2.9276
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1145 - loss: 2.9235
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1148 - loss: 2.9194
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1150 - loss: 2.9154
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1153 - loss: 2.9118
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1156 - loss: 2.9076
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1158 - loss: 2.9053
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1158 - loss: 2.9052 - val_accuracy: 0.1780 - val_loss: 2.3031
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.2923
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1442 - loss: 2.4197  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1548 - loss: 2.4194
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1541 - loss: 2.4363
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1531 - loss: 2.4461
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1538 - loss: 2.4502
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.4543
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1527 - loss: 2.4582
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1521 - loss: 2.4613
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1518 - loss: 2.4627
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1517 - loss: 2.4636
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1520 - loss: 2.4641
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1524 - loss: 2.4639
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1528 - loss: 2.4635
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1532 - loss: 2.4629
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.4621
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1538 - loss: 2.4614
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1540 - loss: 2.4608
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1542 - loss: 2.4602
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1544 - loss: 2.4595
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1545 - loss: 2.4587
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1547 - loss: 2.4580
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1549 - loss: 2.4574
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1551 - loss: 2.4567
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1553 - loss: 2.4562
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4558
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1556 - loss: 2.4553
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1557 - loss: 2.4549
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1558 - loss: 2.4546
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1558 - loss: 2.4542
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1559 - loss: 2.4537
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1560 - loss: 2.4532
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1560 - loss: 2.4527
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1561 - loss: 2.4522
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1562 - loss: 2.4518
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1562 - loss: 2.4512
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1563 - loss: 2.4507
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1564 - loss: 2.4502
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1564 - loss: 2.4497
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1565 - loss: 2.4492
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1566 - loss: 2.4487
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1567 - loss: 2.4482
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1568 - loss: 2.4477
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1569 - loss: 2.4471
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1569 - loss: 2.4467 - val_accuracy: 0.2067 - val_loss: 2.1780
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3859
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1800 - loss: 2.3178  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1736 - loss: 2.3255
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1747 - loss: 2.3250
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1744 - loss: 2.3283
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1745 - loss: 2.3281
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1735 - loss: 2.3292
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1730 - loss: 2.3303
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1725 - loss: 2.3316
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1722 - loss: 2.3331
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1723 - loss: 2.3338
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1722 - loss: 2.3345
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3352
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3357
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3361
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1708 - loss: 2.3368
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1705 - loss: 2.3373
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1704 - loss: 2.3376
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1702 - loss: 2.3378
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1700 - loss: 2.3379
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1700 - loss: 2.3378
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3376
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3376
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1698 - loss: 2.3374
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1698 - loss: 2.3372
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1698 - loss: 2.3369
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3365
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3361
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1700 - loss: 2.3356
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1701 - loss: 2.3352
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1702 - loss: 2.3348
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1702 - loss: 2.3343
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1703 - loss: 2.3339
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1704 - loss: 2.3335
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1705 - loss: 2.3330
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1706 - loss: 2.3326
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1707 - loss: 2.3321
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1707 - loss: 2.3317
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1708 - loss: 2.3312
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3308
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3304
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1710 - loss: 2.3299
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3295
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3291
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3289 - val_accuracy: 0.2309 - val_loss: 2.0945
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.3711
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1704 - loss: 2.2212  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1723 - loss: 2.2567
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1771 - loss: 2.2641
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1794 - loss: 2.2665
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1799 - loss: 2.2654
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1803 - loss: 2.2642
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1806 - loss: 2.2640
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1810 - loss: 2.2646
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1811 - loss: 2.2649
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1813 - loss: 2.2643
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1815 - loss: 2.2643
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.2647
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1818 - loss: 2.2652
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1820 - loss: 2.2653
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1821 - loss: 2.2656
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1822 - loss: 2.2660
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1823 - loss: 2.2664
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1823 - loss: 2.2667
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2673
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2676
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2678
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2679
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1825 - loss: 2.2678
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1825 - loss: 2.2677
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1827 - loss: 2.2675
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.2672
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1829 - loss: 2.2669
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1831 - loss: 2.2666
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.2661
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1833 - loss: 2.2658
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2654
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2650
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2647
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2643
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1838 - loss: 2.2639
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2635
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1840 - loss: 2.2631
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1841 - loss: 2.2626
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1842 - loss: 2.2622
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1842 - loss: 2.2617
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1843 - loss: 2.2614
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1843 - loss: 2.2609
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1844 - loss: 2.2605
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1844 - loss: 2.2604 - val_accuracy: 0.2368 - val_loss: 2.0342
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1250 - loss: 2.2312
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1885 - loss: 2.2694  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1927 - loss: 2.2502
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1973 - loss: 2.2386
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1991 - loss: 2.2369
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2005 - loss: 2.2356
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2015 - loss: 2.2343
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2022 - loss: 2.2336
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2028 - loss: 2.2329
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2035 - loss: 2.2318
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2040 - loss: 2.2305
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2042 - loss: 2.2288
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2043 - loss: 2.2272
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2043 - loss: 2.2260
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2042 - loss: 2.2250
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2040 - loss: 2.2242
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2038 - loss: 2.2234
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2037 - loss: 2.2225
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2035 - loss: 2.2216
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2033 - loss: 2.2206
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2032 - loss: 2.2196
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2032 - loss: 2.2186
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2031 - loss: 2.2176
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2030 - loss: 2.2166
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2030 - loss: 2.2157
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2030 - loss: 2.2150
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2029 - loss: 2.2143
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2029 - loss: 2.2138
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2029 - loss: 2.2133
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2029 - loss: 2.2128
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2029 - loss: 2.2122
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2029 - loss: 2.2117
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2029 - loss: 2.2111
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2030 - loss: 2.2104
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2031 - loss: 2.2097
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2031 - loss: 2.2090
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2032 - loss: 2.2083
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2033 - loss: 2.2076
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2034 - loss: 2.2068
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2034 - loss: 2.2061
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2035 - loss: 2.2053
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2035 - loss: 2.2048
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2035 - loss: 2.2041
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2036 - loss: 2.2035
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2036 - loss: 2.2033 - val_accuracy: 0.2588 - val_loss: 1.9814
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.4898
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2454 - loss: 2.1867  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2464 - loss: 2.1526
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2443 - loss: 2.1457
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2399 - loss: 2.1434
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2374 - loss: 2.1415
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2353 - loss: 2.1414
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2337 - loss: 2.1410
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2327 - loss: 2.1404
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2318 - loss: 2.1411
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2305 - loss: 2.1423
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2294 - loss: 2.1431
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2285 - loss: 2.1436
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2278 - loss: 2.1438
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2274 - loss: 2.1438
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2269 - loss: 2.1437
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.1437
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2263 - loss: 2.1438
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2261 - loss: 2.1437
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2258 - loss: 2.1438
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.1439
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2253 - loss: 2.1441
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2251 - loss: 2.1442
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2250 - loss: 2.1442
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2249 - loss: 2.1442
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2248 - loss: 2.1439
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2247 - loss: 2.1438
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.1436
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.1433
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2244 - loss: 2.1431
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2244 - loss: 2.1429
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2244 - loss: 2.1426
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2243 - loss: 2.1424
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2243 - loss: 2.1421
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2243 - loss: 2.1419
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2242 - loss: 2.1416
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2242 - loss: 2.1414
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2242 - loss: 2.1411
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2242 - loss: 2.1409
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2242 - loss: 2.1406
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1403
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1401
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1398
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1396
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1393
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1393 - val_accuracy: 0.2746 - val_loss: 1.9609
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1271
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2520 - loss: 2.1462  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2494 - loss: 2.1216
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2464 - loss: 2.1128
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2439 - loss: 2.1021
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2418 - loss: 2.0983
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2412 - loss: 2.0969
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2406 - loss: 2.0968
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2404 - loss: 2.0967
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2400 - loss: 2.0965
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2395 - loss: 2.0969
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2387 - loss: 2.0976
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.0979
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.0979
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.0978
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2375 - loss: 2.0977
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2373 - loss: 2.0979
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2369 - loss: 2.0983
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2366 - loss: 2.0987
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2365 - loss: 2.0988
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2363 - loss: 2.0989
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2361 - loss: 2.0989
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.0989
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2359 - loss: 2.0989
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2358 - loss: 2.0988
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.0988
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2355 - loss: 2.0988
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2355 - loss: 2.0986
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2354 - loss: 2.0985
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2354 - loss: 2.0983
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2355 - loss: 2.0981
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2355 - loss: 2.0980
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.0979
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.0978
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2357 - loss: 2.0976
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2358 - loss: 2.0975
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2359 - loss: 2.0973
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2360 - loss: 2.0973
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2361 - loss: 2.0972
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2362 - loss: 2.0971
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2363 - loss: 2.0970
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2364 - loss: 2.0968
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2365 - loss: 2.0966
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2366 - loss: 2.0964
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2368 - loss: 2.0962 - val_accuracy: 0.3110 - val_loss: 1.9099
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.1250 - loss: 2.2040
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2793 - loss: 1.9790  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2741 - loss: 2.0006
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2693 - loss: 2.0080
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2663 - loss: 2.0125
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0150
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0161
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.0190
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2610 - loss: 2.0221
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2604 - loss: 2.0242
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.0263
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2592 - loss: 2.0280
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2586 - loss: 2.0297
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2581 - loss: 2.0308
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2578 - loss: 2.0313
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2578 - loss: 2.0313
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2578 - loss: 2.0316
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2579 - loss: 2.0317
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2581 - loss: 2.0319
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2583 - loss: 2.0321
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2584 - loss: 2.0321
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2585 - loss: 2.0322
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2585 - loss: 2.0321
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2586 - loss: 2.0319
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2586 - loss: 2.0317
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.0316
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.0316
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.0315
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.0314
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.0313
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.0312
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2592 - loss: 2.0311
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 2.0310
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.0311
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.0311
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2596 - loss: 2.0311
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.0310
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.0310
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.0310
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2601 - loss: 2.0309
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.0309
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.0308
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.0307
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2606 - loss: 2.0306
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.0305
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2609 - loss: 2.0304 - val_accuracy: 0.3360 - val_loss: 1.8756
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9451
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2806 - loss: 2.0031  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2835 - loss: 2.0062
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2866 - loss: 2.0053
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2883 - loss: 2.0051
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2877 - loss: 2.0059
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2875 - loss: 2.0053
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2867 - loss: 2.0058
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.0059
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2850 - loss: 2.0059
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.0061
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 2.0058
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.0054
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 2.0050
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.0044
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.0039
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 2.0033
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.0025
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.0017
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.0011
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.0004
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2854 - loss: 1.9997
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 1.9989
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 1.9982
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 1.9977
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2863 - loss: 1.9973
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2864 - loss: 1.9969
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2864 - loss: 1.9966
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2865 - loss: 1.9961
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2866 - loss: 1.9957
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2866 - loss: 1.9952
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2866 - loss: 1.9947
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2866 - loss: 1.9942
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 1.9939
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 1.9935
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 1.9931
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 1.9928
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 1.9925
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2869 - loss: 1.9921
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2869 - loss: 1.9918
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2870 - loss: 1.9915
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2870 - loss: 1.9911
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2871 - loss: 1.9908
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2871 - loss: 1.9905
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2872 - loss: 1.9901
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2872 - loss: 1.9901 - val_accuracy: 0.2990 - val_loss: 1.8862
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.1154
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2819 - loss: 1.9988  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2840 - loss: 1.9988
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2837 - loss: 1.9973
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2812 - loss: 1.9958
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2798 - loss: 1.9949
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2797 - loss: 1.9944
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9947
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 1.9941
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 1.9926
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 1.9910
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 1.9893
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2826 - loss: 1.9872
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 1.9849
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 1.9827
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 1.9807
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2854 - loss: 1.9787
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 1.9770
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2864 - loss: 1.9752
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2870 - loss: 1.9734
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2873 - loss: 1.9718
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2877 - loss: 1.9702
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 1.9688
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2886 - loss: 1.9677
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 1.9666
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2893 - loss: 1.9656
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2897 - loss: 1.9644
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2901 - loss: 1.9634
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2905 - loss: 1.9625
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2908 - loss: 1.9618
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2912 - loss: 1.9609
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2916 - loss: 1.9602
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 1.9595
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 1.9588
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 1.9581
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9574
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 1.9568
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2932 - loss: 1.9562
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2934 - loss: 1.9557
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9552
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2939 - loss: 1.9546
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 1.9541
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 1.9536
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 1.9532
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9527
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 1.9522
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2949 - loss: 1.9521 - val_accuracy: 0.3806 - val_loss: 1.7893
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3083
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2518 - loss: 2.0213  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2773 - loss: 2.0009
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2884 - loss: 1.9874
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2945 - loss: 1.9729
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 1.9638
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 1.9581
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 1.9532
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 1.9496
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 1.9457
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3120 - loss: 1.9425
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 1.9396
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.9371
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9345
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 1.9322
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 1.9306
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 1.9292
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 1.9278
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 1.9266
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 1.9255
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 1.9243
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 1.9232
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 1.9221
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 1.9212
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 1.9204
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9198
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9193
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9188
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9182
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 1.9177
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 1.9171
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 1.9165
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 1.9160
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 1.9155
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 1.9151
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9146
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9141
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9136
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9131
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9127
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9123
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9118
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9113
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 1.9109
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3153 - loss: 1.9105 - val_accuracy: 0.3136 - val_loss: 1.8278
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7095
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3795 - loss: 1.8261  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3769 - loss: 1.8151
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3704 - loss: 1.8238
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3666 - loss: 1.8260
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3630 - loss: 1.8302
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3604 - loss: 1.8315
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3585 - loss: 1.8321
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3569 - loss: 1.8329
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3552 - loss: 1.8339
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3535 - loss: 1.8346
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3516 - loss: 1.8351
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3498 - loss: 1.8366
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8373
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3480 - loss: 1.8382
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3472 - loss: 1.8388
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 1.8395
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3456 - loss: 1.8403
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3449 - loss: 1.8410
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3443 - loss: 1.8415
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 1.8420
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 1.8424
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8429
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.8431
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8435
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8437
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3409 - loss: 1.8438
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3406 - loss: 1.8438
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8438
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8438
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8438
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8439
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8441
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8441
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8441
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8441
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8440
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8440
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.8440
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3373 - loss: 1.8439
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8438
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3369 - loss: 1.8438
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3367 - loss: 1.8438
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8438
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8438
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8438 - val_accuracy: 0.3230 - val_loss: 1.8245
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.9587
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3240 - loss: 1.7614  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3286 - loss: 1.7858
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8044
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3327 - loss: 1.8115
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3343 - loss: 1.8149
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8157
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8166
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8176
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8187
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8195
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8203
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 1.8214
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8222
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3349 - loss: 1.8232
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8242
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8252
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8262
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8269
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 1.8276
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8281
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8287
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8293
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8297
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8300
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8302
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8303
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8303
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8304
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8304
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8304
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8303
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8303
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3341 - loss: 1.8303
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8303
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8303
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3343 - loss: 1.8303
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8303
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8303
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8303
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3346 - loss: 1.8304
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3346 - loss: 1.8304
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8304
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8304
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8303
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3348 - loss: 1.8303 - val_accuracy: 0.3824 - val_loss: 1.7493
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.7922
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3344 - loss: 1.7674  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3318 - loss: 1.7817
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3334 - loss: 1.7911
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3350 - loss: 1.7978
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8024
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8057
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8079
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8081
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8077
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8069
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8066
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8063
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8061
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8057
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8053
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8049
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3411 - loss: 1.8044
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8038
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8033
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3424 - loss: 1.8027
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8023
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3431 - loss: 1.8018
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3434 - loss: 1.8015
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3438 - loss: 1.8011
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3441 - loss: 1.8008
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3443 - loss: 1.8005
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3446 - loss: 1.8002
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3449 - loss: 1.7999
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3451 - loss: 1.7997
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3453 - loss: 1.7995
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7993
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3458 - loss: 1.7991
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3460 - loss: 1.7989
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3461 - loss: 1.7988
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3463 - loss: 1.7986
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3464 - loss: 1.7984
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3465 - loss: 1.7983
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3466 - loss: 1.7981
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3467 - loss: 1.7980
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3468 - loss: 1.7979
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3469 - loss: 1.7978
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3469 - loss: 1.7977
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3470 - loss: 1.7977
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3470 - loss: 1.7976
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7976 - val_accuracy: 0.3532 - val_loss: 1.7761
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.5003
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7252  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7229
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7236
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7277
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7329
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7392
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7444
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7472
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7504
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7537
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7561
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7576
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7591
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7603
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3556 - loss: 1.7612
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3553 - loss: 1.7620
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3551 - loss: 1.7628
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7638
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7647
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7653
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7658
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7662
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7665
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7668
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7673
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7678
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7681
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7685
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7689
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7694
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7698
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7701
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7706
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7709
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7712
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7715
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7718
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7720
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7722
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7723
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7724
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7725
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7726
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7726
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7726 - val_accuracy: 0.3513 - val_loss: 1.7632
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.6250 - loss: 1.4995
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7835  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7934
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3527 - loss: 1.7991
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3489 - loss: 1.8042
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8039
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.8005
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3504 - loss: 1.7961
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7915
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7879
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3527 - loss: 1.7847
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7820
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7794
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7768
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3555 - loss: 1.7749
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7728
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7707
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7688
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7669
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7652
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7638
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7628
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7617
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7610
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7603
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7597
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7592
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7587
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7583
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7579
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7575
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7571
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7567
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3617 - loss: 1.7564
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7561
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7559
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7557
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7555
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7553
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7550
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7548
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7546
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7543
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7541
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7538
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7537 - val_accuracy: 0.3854 - val_loss: 1.7469
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7149
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3904 - loss: 1.6584  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3785 - loss: 1.6939
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7094
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7144
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7205
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3700 - loss: 1.7260
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7275
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7285
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7286
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7291
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7293
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7294
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7295
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3691 - loss: 1.7293
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3691 - loss: 1.7290
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3692 - loss: 1.7288
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7286
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7286
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7285
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7283
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7282
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7280
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7278
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7275
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7273
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7271
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3701 - loss: 1.7269
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7267
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7266
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3704 - loss: 1.7265
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3704 - loss: 1.7263
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3704 - loss: 1.7260
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7258
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7255
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7254
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7252
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7250
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7248
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7246
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7245
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7243
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7241
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7239
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7238 - val_accuracy: 0.3813 - val_loss: 1.7555
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.6541
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3691 - loss: 1.6965  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3697 - loss: 1.6965
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7012
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7024
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7017
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7025
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3747 - loss: 1.7026
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3758 - loss: 1.7023
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7019
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7014
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7010
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7012
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7015
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3770 - loss: 1.7019
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7018
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3768 - loss: 1.7016
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3770 - loss: 1.7011
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7007
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3773 - loss: 1.7003
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7000
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3776 - loss: 1.6999
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6999
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3778 - loss: 1.6999
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3779 - loss: 1.6998
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3781 - loss: 1.6997
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.6996
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.6995
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.6996
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3787 - loss: 1.6995
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3789 - loss: 1.6994
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3790 - loss: 1.6993
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3792 - loss: 1.6992
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3794 - loss: 1.6991
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6990
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3796 - loss: 1.6990
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3797 - loss: 1.6990
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3797 - loss: 1.6990
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3798 - loss: 1.6990
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3799 - loss: 1.6990
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3799 - loss: 1.6990
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3799 - loss: 1.6989
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3800 - loss: 1.6989
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3800 - loss: 1.6990
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3800 - loss: 1.6990 - val_accuracy: 0.3512 - val_loss: 1.7971
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.5507
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4366 - loss: 1.5968  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4388 - loss: 1.5938
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4318 - loss: 1.6077
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4250 - loss: 1.6226
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4209 - loss: 1.6312
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4179 - loss: 1.6361
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4161 - loss: 1.6405
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4148 - loss: 1.6437
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4140 - loss: 1.6453
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4136 - loss: 1.6464
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4129 - loss: 1.6475
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4124 - loss: 1.6480
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4119 - loss: 1.6483
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4116 - loss: 1.6486
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4113 - loss: 1.6489
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4108 - loss: 1.6498
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4102 - loss: 1.6508
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4095 - loss: 1.6519
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4089 - loss: 1.6530
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4083 - loss: 1.6540
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4077 - loss: 1.6549
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4072 - loss: 1.6556
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4067 - loss: 1.6562
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4062 - loss: 1.6567
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4057 - loss: 1.6573
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4052 - loss: 1.6580
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4047 - loss: 1.6586
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4042 - loss: 1.6592
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4037 - loss: 1.6598
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4032 - loss: 1.6603
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4028 - loss: 1.6608
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4024 - loss: 1.6613
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4020 - loss: 1.6618
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4017 - loss: 1.6622
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4013 - loss: 1.6626
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4010 - loss: 1.6630
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4007 - loss: 1.6633
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4004 - loss: 1.6637
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4001 - loss: 1.6639
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3999 - loss: 1.6642
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3996 - loss: 1.6644
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3993 - loss: 1.6646
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3991 - loss: 1.6649
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3988 - loss: 1.6650
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3988 - loss: 1.6651 - val_accuracy: 0.3841 - val_loss: 1.7516
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.5723
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4260 - loss: 1.6113  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4187 - loss: 1.6464
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4200 - loss: 1.6532
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4171 - loss: 1.6612
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4132 - loss: 1.6661
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4096 - loss: 1.6693
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4070 - loss: 1.6716
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4051 - loss: 1.6733
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4041 - loss: 1.6731
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4033 - loss: 1.6726
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4026 - loss: 1.6723
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4020 - loss: 1.6721
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4012 - loss: 1.6721
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4006 - loss: 1.6724
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4001 - loss: 1.6724
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3997 - loss: 1.6724
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3994 - loss: 1.6723
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3991 - loss: 1.6719
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3989 - loss: 1.6716
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3987 - loss: 1.6713
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3985 - loss: 1.6710
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3984 - loss: 1.6709
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6706
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6701
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6696
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6691
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6686
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6682
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6679
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6676
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3981 - loss: 1.6672
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3981 - loss: 1.6669
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3981 - loss: 1.6665
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3981 - loss: 1.6661
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3980 - loss: 1.6657
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3980 - loss: 1.6654
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3980 - loss: 1.6651
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3980 - loss: 1.6649
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3980 - loss: 1.6647
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3980 - loss: 1.6644
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3979 - loss: 1.6642
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3979 - loss: 1.6640
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3978 - loss: 1.6639
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3977 - loss: 1.6638 - val_accuracy: 0.3676 - val_loss: 1.7700
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.2184
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4476 - loss: 1.5405  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4173 - loss: 1.6260
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4086 - loss: 1.6569
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4047 - loss: 1.6749
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6833
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3990 - loss: 1.6858
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6858
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3977 - loss: 1.6855
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6850
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3962 - loss: 1.6845
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6829
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3964 - loss: 1.6808
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6787
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6769
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3977 - loss: 1.6749
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3981 - loss: 1.6735
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3984 - loss: 1.6723
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3986 - loss: 1.6713
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3987 - loss: 1.6704
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3988 - loss: 1.6695
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3990 - loss: 1.6685
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3991 - loss: 1.6675
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3991 - loss: 1.6668
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3992 - loss: 1.6659
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3992 - loss: 1.6652
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3991 - loss: 1.6644
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3991 - loss: 1.6637
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3990 - loss: 1.6630
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3989 - loss: 1.6625
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3988 - loss: 1.6620
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3988 - loss: 1.6615
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3987 - loss: 1.6611
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3986 - loss: 1.6608
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3986 - loss: 1.6604
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3985 - loss: 1.6602
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3984 - loss: 1.6600
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3983 - loss: 1.6599
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6597
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6595
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3981 - loss: 1.6592
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3981 - loss: 1.6591
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3980 - loss: 1.6589
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3980 - loss: 1.6588
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3979 - loss: 1.6586
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3979 - loss: 1.6586 - val_accuracy: 0.3865 - val_loss: 1.7581

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 1s/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:21:10.063408: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.

=== EJECUCIÓN 1 ===

--- TRAIN (ejecución 1) ---

--- TEST (ejecución 1) ---
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:30[0m 1s/step
[1m 52/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 994us/step
[1m108/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 948us/step
[1m162/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 943us/step
[1m219/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 928us/step
[1m273/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 929us/step
[1m329/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 924us/step
[1m383/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 925us/step
[1m437/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 927us/step
[1m499/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 912us/step
[1m560/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 902us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 963us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 998us/step
[1m108/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 949us/step
[1m156/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 979us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 37.95 [%]
Global F1 score (validation) = 35.76 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.22730859 0.21376455 0.2083911  ... 0.00539049 0.16858147 0.09600936]
 [0.21612132 0.23520742 0.20029661 ... 0.00448134 0.16017771 0.00851645]
 [0.19377121 0.23463461 0.19351938 ... 0.01905257 0.13014841 0.0124419 ]
 ...
 [0.0996704  0.13098337 0.08155906 ... 0.00905099 0.05654579 0.00435187]
 [0.21223609 0.18721685 0.19764216 ... 0.00074343 0.19157383 0.01686398]
 [0.24245079 0.24264751 0.2107256  ... 0.00233379 0.17956634 0.01763079]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.48 [%]
Global accuracy score (test) = 33.14 [%]
Global F1 score (train) = 43.43 [%]
Global F1 score (test) = 31.03 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.15      0.22      0.18       184
 CAMINAR CON MÓVIL O LIBRO       0.20      0.48      0.29       184
       CAMINAR USUAL SPEED       0.00      0.00      0.00       184
            CAMINAR ZIGZAG       0.51      0.51      0.51       184
          DE PIE BARRIENDO       0.28      0.33      0.30       184
   DE PIE DOBLANDO TOALLAS       0.39      0.07      0.12       184
    DE PIE MOVIENDO LIBROS       0.31      0.58      0.40       184
          DE PIE USANDO PC       0.29      0.61      0.40       184
        FASE REPOSO CON K5       0.67      0.54      0.60       184
INCREMENTAL CICLOERGOMETRO       0.70      0.42      0.52       184
           SENTADO LEYENDO       0.27      0.18      0.22       184
         SENTADO USANDO PC       0.37      0.24      0.29       184
      SENTADO VIENDO LA TV       0.44      0.38      0.41       184
   SUBIR Y BAJAR ESCALERAS       0.14      0.02      0.04       184
                    TROTAR       0.38      0.39      0.38       161

                  accuracy                           0.33      2737
                 macro avg       0.34      0.33      0.31      2737
              weighted avg       0.34      0.33      0.31      2737


Accuracy capturado en la ejecución 1: 33.14 [%]
F1-score capturado en la ejecución 1: 31.03 [%]

=== EJECUCIÓN 2 ===

--- TRAIN (ejecución 2) ---

--- TEST (ejecución 2) ---
2025-10-31 15:21:23.450241: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:21:23.461606: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761920483.474852 1646109 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761920483.479071 1646109 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761920483.488854 1646109 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920483.488876 1646109 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920483.488878 1646109 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920483.488888 1646109 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:21:23.492134: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761920485.869194 1646109 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761920488.993367 1646210 service.cc:152] XLA service 0x7879dc017840 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761920488.993405 1646210 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:21:29.057422: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761920489.506696 1646210 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761920492.139939 1646210 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:13[0m 6s/step - accuracy: 0.0000e+00 - loss: 3.5038
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0732 - loss: 3.3751        
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0871 - loss: 3.2805
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0914 - loss: 3.2427
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0940 - loss: 3.2217
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0953 - loss: 3.2052
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0959 - loss: 3.1928
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0963 - loss: 3.1850
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0965 - loss: 3.1768
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0967 - loss: 3.1691
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0968 - loss: 3.1627
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0969 - loss: 3.1559
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0970 - loss: 3.1499
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0970 - loss: 3.1444
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0971 - loss: 3.1380
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0972 - loss: 3.1316
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0974 - loss: 3.1258
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0976 - loss: 3.1205
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0979 - loss: 3.1142
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0983 - loss: 3.1077
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0986 - loss: 3.1026
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0989 - loss: 3.0966
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0992 - loss: 3.0911
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0995 - loss: 3.0854
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0998 - loss: 3.0803
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1001 - loss: 3.0752
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1004 - loss: 3.0704
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1007 - loss: 3.0656
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1010 - loss: 3.0608
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1013 - loss: 3.0561
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1016 - loss: 3.0514
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1019 - loss: 3.0467
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1023 - loss: 3.0420
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1026 - loss: 3.0378
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1028 - loss: 3.0333
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1031 - loss: 3.0289
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1034 - loss: 3.0252
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1036 - loss: 3.0213
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1038 - loss: 3.0177
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1041 - loss: 3.0135
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1043 - loss: 3.0093
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1046 - loss: 3.0049
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1049 - loss: 3.0005
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1051 - loss: 2.9963
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1051 - loss: 2.9960
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1051 - loss: 2.9959 - val_accuracy: 0.1404 - val_loss: 2.3995
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1250 - loss: 2.8396
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1189 - loss: 2.6759  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1206 - loss: 2.6638
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1212 - loss: 2.6489
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1232 - loss: 2.6386
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1259 - loss: 2.6302
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1273 - loss: 2.6247
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1279 - loss: 2.6200
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1288 - loss: 2.6158
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1296 - loss: 2.6116
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1307 - loss: 2.6073
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1317 - loss: 2.6034
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1327 - loss: 2.5998
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1336 - loss: 2.5960
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1344 - loss: 2.5924
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1350 - loss: 2.5896
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1355 - loss: 2.5872
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1359 - loss: 2.5848
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1362 - loss: 2.5829
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1365 - loss: 2.5807
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1369 - loss: 2.5787
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1372 - loss: 2.5766
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1376 - loss: 2.5747
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1380 - loss: 2.5726
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1384 - loss: 2.5704
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1387 - loss: 2.5686
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1390 - loss: 2.5669
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1392 - loss: 2.5652
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1395 - loss: 2.5634
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1398 - loss: 2.5616
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1401 - loss: 2.5600
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1403 - loss: 2.5585
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1406 - loss: 2.5568
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1408 - loss: 2.5552
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1411 - loss: 2.5536
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1413 - loss: 2.5520
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1416 - loss: 2.5505
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1418 - loss: 2.5490
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1420 - loss: 2.5474
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1421 - loss: 2.5461
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1423 - loss: 2.5446
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1424 - loss: 2.5433
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1426 - loss: 2.5419
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1428 - loss: 2.5406
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1428 - loss: 2.5400 - val_accuracy: 0.1697 - val_loss: 2.2463
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0425
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1996 - loss: 2.3409  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1884 - loss: 2.3220
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1826 - loss: 2.3281
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1777 - loss: 2.3338
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1740 - loss: 2.3390
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1721 - loss: 2.3435
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1710 - loss: 2.3459
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3479
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1691 - loss: 2.3494
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3511
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3523
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1675 - loss: 2.3534
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1670 - loss: 2.3548
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3559
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1665 - loss: 2.3566
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1663 - loss: 2.3571
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1660 - loss: 2.3575
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1658 - loss: 2.3578
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1656 - loss: 2.3581
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1655 - loss: 2.3580
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1654 - loss: 2.3580
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3581
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1651 - loss: 2.3581
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3581
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3580
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1649 - loss: 2.3579
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1649 - loss: 2.3577
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1649 - loss: 2.3576
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3574
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3573
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3572
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3569
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3567
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3564
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3562
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3559
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1649 - loss: 2.3557
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1649 - loss: 2.3554
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3551
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3548
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1651 - loss: 2.3544
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3541
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3538
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1653 - loss: 2.3536 - val_accuracy: 0.2041 - val_loss: 2.1609
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4948
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1535 - loss: 2.2844  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1689 - loss: 2.2674
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1722 - loss: 2.2733
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1717 - loss: 2.2803
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1709 - loss: 2.2871
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1708 - loss: 2.2917
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1708 - loss: 2.2945
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1716 - loss: 2.2941
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1724 - loss: 2.2931
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1735 - loss: 2.2915
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1746 - loss: 2.2899
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1754 - loss: 2.2887
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1759 - loss: 2.2879
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1763 - loss: 2.2874
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1767 - loss: 2.2866
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1770 - loss: 2.2859
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1773 - loss: 2.2852
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.2849
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1776 - loss: 2.2848
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.2847
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.2844
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1782 - loss: 2.2842
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1783 - loss: 2.2841
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1784 - loss: 2.2839
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1785 - loss: 2.2837
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1787 - loss: 2.2833
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1789 - loss: 2.2830
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1791 - loss: 2.2826
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.2823
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.2820
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.2818
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.2815
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1799 - loss: 2.2812
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1801 - loss: 2.2809
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.2807
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.2804
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1806 - loss: 2.2800
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1807 - loss: 2.2797
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1808 - loss: 2.2794
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1809 - loss: 2.2790
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1810 - loss: 2.2787
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1810 - loss: 2.2785
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1811 - loss: 2.2783 - val_accuracy: 0.2076 - val_loss: 2.0925
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.6479
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2040 - loss: 2.3184  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1921 - loss: 2.2996
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1911 - loss: 2.2902
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1909 - loss: 2.2832
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1913 - loss: 2.2773
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1920 - loss: 2.2718
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1924 - loss: 2.2675
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1922 - loss: 2.2646
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1916 - loss: 2.2634
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2628
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1903 - loss: 2.2624
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1899 - loss: 2.2621
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1896 - loss: 2.2622
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1892 - loss: 2.2621
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1890 - loss: 2.2617
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1891 - loss: 2.2612
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1891 - loss: 2.2608
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1892 - loss: 2.2604
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1893 - loss: 2.2599
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1894 - loss: 2.2594
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1895 - loss: 2.2588
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1896 - loss: 2.2579
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1897 - loss: 2.2571
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1897 - loss: 2.2563
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1898 - loss: 2.2555
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1899 - loss: 2.2547
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1899 - loss: 2.2538
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1901 - loss: 2.2530
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1902 - loss: 2.2521
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1904 - loss: 2.2512
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2504
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2496
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1909 - loss: 2.2488
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1911 - loss: 2.2480
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1913 - loss: 2.2471
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1915 - loss: 2.2464
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1916 - loss: 2.2457
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1917 - loss: 2.2449
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1919 - loss: 2.2442
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1920 - loss: 2.2434
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1921 - loss: 2.2428
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1922 - loss: 2.2422
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1923 - loss: 2.2415
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1924 - loss: 2.2411 - val_accuracy: 0.2146 - val_loss: 2.0441
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.6987
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2062 - loss: 2.2655  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2005 - loss: 2.2413
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1999 - loss: 2.2306
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2215
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2022 - loss: 2.2157
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2020 - loss: 2.2127
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2013 - loss: 2.2108
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2008 - loss: 2.2092
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2074
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2011 - loss: 2.2049
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2017 - loss: 2.2020
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.2001
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2026 - loss: 2.1981
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2031 - loss: 2.1961
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2035 - loss: 2.1947
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2039 - loss: 2.1936
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2041 - loss: 2.1929
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2043 - loss: 2.1921
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.1915
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2047 - loss: 2.1908
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2048 - loss: 2.1903
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2049 - loss: 2.1895
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2051 - loss: 2.1888
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2052 - loss: 2.1881
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2054 - loss: 2.1872
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2056 - loss: 2.1864
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2058 - loss: 2.1857
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2060 - loss: 2.1851
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2062 - loss: 2.1843
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.1836
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2066 - loss: 2.1828
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2068 - loss: 2.1819
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2070 - loss: 2.1811
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2072 - loss: 2.1803
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2074 - loss: 2.1795
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.1789
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2076 - loss: 2.1782
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2078 - loss: 2.1775
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2080 - loss: 2.1768
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2081 - loss: 2.1763
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.1757
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2083 - loss: 2.1752
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2084 - loss: 2.1746
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2085 - loss: 2.1743 - val_accuracy: 0.2194 - val_loss: 2.0681
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7981
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2352 - loss: 2.1123  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2169 - loss: 2.1298
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2158 - loss: 2.1273
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.1274
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2194 - loss: 2.1280
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2207 - loss: 2.1275
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2221 - loss: 2.1267
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2232 - loss: 2.1265
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2240 - loss: 2.1257
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2246 - loss: 2.1243
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2251 - loss: 2.1233
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1229
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2253 - loss: 2.1225
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2254 - loss: 2.1219
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2254 - loss: 2.1215
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.1211
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2254 - loss: 2.1208
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2253 - loss: 2.1207
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2253 - loss: 2.1207
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1206
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1204
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2253 - loss: 2.1202
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.1201
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.1199
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2257 - loss: 2.1196
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2258 - loss: 2.1193
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2260 - loss: 2.1190
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2261 - loss: 2.1188
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2262 - loss: 2.1185
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2264 - loss: 2.1183
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2265 - loss: 2.1179
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2266 - loss: 2.1177
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2267 - loss: 2.1175
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2269 - loss: 2.1172
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2270 - loss: 2.1169
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2271 - loss: 2.1166
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2273 - loss: 2.1164
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2274 - loss: 2.1161
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2276 - loss: 2.1159
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2277 - loss: 2.1156
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2279 - loss: 2.1154
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2280 - loss: 2.1152
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2281 - loss: 2.1151 - val_accuracy: 0.2512 - val_loss: 2.0166
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0006
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2607 - loss: 2.0496  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2584 - loss: 2.0478
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2537 - loss: 2.0602
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2514 - loss: 2.0624
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2509 - loss: 2.0613
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2509 - loss: 2.0601
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2511 - loss: 2.0590
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.0584
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.0582
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2509 - loss: 2.0582
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.0586
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.0587
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.0586
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.0587
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.0591
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.0596
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.0601
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.0604
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.0606
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.0610
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2506 - loss: 2.0613
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0615
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0618
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0621
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0622
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0625
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0627
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0628
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0630
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0632
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0634
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0636
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0637
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0637
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0638
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0639
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0640
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0640
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2506 - loss: 2.0640
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2506 - loss: 2.0640
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2507 - loss: 2.0640
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2507 - loss: 2.0640
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2508 - loss: 2.0640
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2508 - loss: 2.0640 - val_accuracy: 0.3008 - val_loss: 1.9395
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2971
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2780 - loss: 2.1634  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1302
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1125
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2754 - loss: 2.0994
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2756 - loss: 2.0857
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2751 - loss: 2.0765
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2743 - loss: 2.0699
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.0645
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2739 - loss: 2.0602
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2736 - loss: 2.0567
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2732 - loss: 2.0540
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 2.0519
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 2.0503
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0489
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0475
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2724 - loss: 2.0463
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2723 - loss: 2.0456
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2721 - loss: 2.0447
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0441
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2718 - loss: 2.0438
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0432
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.0425
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.0420
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0416
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2712 - loss: 2.0412
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0406
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0401
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0395
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0389
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0384
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0377
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0372
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0366
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0360
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0356
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0351
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0346
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0342
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0337
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0334
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0331
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0328
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0325
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0325 - val_accuracy: 0.2846 - val_loss: 1.9427
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.7781
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2489 - loss: 1.9978  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0057
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2679 - loss: 2.0073
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2696 - loss: 2.0092
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0106
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.0116
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.0112
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0112
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0105
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0098
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 2.0094
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2729 - loss: 2.0093
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2730 - loss: 2.0093
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2731 - loss: 2.0092
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.0089
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2737 - loss: 2.0083
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.0075
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2744 - loss: 2.0067
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2748 - loss: 2.0059
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2752 - loss: 2.0050
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2755 - loss: 2.0043
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 2.0036
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2761 - loss: 2.0028
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 2.0020
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 2.0013
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.0007
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.0001
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 1.9995
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2773 - loss: 1.9991
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 1.9986
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2775 - loss: 1.9982
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2777 - loss: 1.9977
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 1.9971
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 1.9967
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2780 - loss: 1.9963
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2781 - loss: 1.9959
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2783 - loss: 1.9955
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2784 - loss: 1.9952
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2785 - loss: 1.9947
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2786 - loss: 1.9943
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 1.9939
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2788 - loss: 1.9934
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2789 - loss: 1.9930
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2790 - loss: 1.9927 - val_accuracy: 0.2981 - val_loss: 1.9164
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.5343
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3290 - loss: 1.9026  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3245 - loss: 1.9407
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3171 - loss: 1.9549
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3121 - loss: 1.9611
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3077 - loss: 1.9705
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 1.9759
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 1.9773
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9776
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 1.9777
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9770
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 1.9763
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9757
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 1.9750
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9740
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2949 - loss: 1.9729
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9718
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2944 - loss: 1.9707
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 1.9697
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 1.9689
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9683
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 1.9677
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 1.9669
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9661
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9655
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2935 - loss: 1.9649
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2934 - loss: 1.9644
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2934 - loss: 1.9638
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2934 - loss: 1.9631
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2934 - loss: 1.9623
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2935 - loss: 1.9617
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2935 - loss: 1.9611
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2935 - loss: 1.9605
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9599
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9593
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9588
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9583
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9579
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9574
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2937 - loss: 1.9569
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2937 - loss: 1.9565
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2937 - loss: 1.9561
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9557
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9553
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9549 - val_accuracy: 0.3166 - val_loss: 1.8830
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.6326
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3083 - loss: 1.9053  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3113 - loss: 1.8952
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3080 - loss: 1.8943
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3037 - loss: 1.8956
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 1.8971
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 1.8999
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 1.9018
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9043
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9062
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9082
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9098
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9108
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9113
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9113
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9112
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2989 - loss: 1.9114
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2991 - loss: 1.9113
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 1.9113
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 1.9112
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 1.9113
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 1.9114
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 1.9113
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3001 - loss: 1.9113
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 1.9113
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 1.9111
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9109
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9108
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 1.9108
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 1.9109
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 1.9111
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3014 - loss: 1.9111
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 1.9111
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9111
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 1.9111
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3019 - loss: 1.9111
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 1.9110
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 1.9110
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3021 - loss: 1.9109
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 1.9108
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 1.9107
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 1.9106
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 1.9104
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3026 - loss: 1.9103 - val_accuracy: 0.3195 - val_loss: 1.8628
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2245
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3531 - loss: 1.8386  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3560 - loss: 1.8315
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3561 - loss: 1.8353
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3513 - loss: 1.8408
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 1.8481
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8535
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8568
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8584
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8591
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8605
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8614
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8626
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 1.8635
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 1.8642
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 1.8648
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8650
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8650
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 1.8651
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8652
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 1.8653
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3293 - loss: 1.8653
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3290 - loss: 1.8654
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 1.8655
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8658
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3282 - loss: 1.8661
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3279 - loss: 1.8664
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 1.8667
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 1.8669
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3270 - loss: 1.8671
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 1.8674
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3265 - loss: 1.8677
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8680
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3261 - loss: 1.8683
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8685
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 1.8689
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 1.8691
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 1.8694
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 1.8697
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 1.8699
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 1.8701
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 1.8702
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8704
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3245 - loss: 1.8706
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8708
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3243 - loss: 1.8708 - val_accuracy: 0.2910 - val_loss: 1.9204
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 1.7976
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2790 - loss: 1.8380  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2958 - loss: 1.8734
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2994 - loss: 1.8858
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3030 - loss: 1.8881
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3053 - loss: 1.8865
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3085 - loss: 1.8818
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8779
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 1.8751
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 1.8719
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3167 - loss: 1.8690
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8667
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8647
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8632
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 1.8618
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 1.8602
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 1.8592
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3216 - loss: 1.8584
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 1.8575
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 1.8566
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3225 - loss: 1.8557
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3228 - loss: 1.8551
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3230 - loss: 1.8545
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3232 - loss: 1.8539
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 1.8535
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 1.8532
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 1.8528
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 1.8524
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 1.8521
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 1.8518
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 1.8515
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8513
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3242 - loss: 1.8511
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3243 - loss: 1.8510
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8509
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8508
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8507
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 1.8505
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3250 - loss: 1.8503
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 1.8502
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 1.8501
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 1.8500
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 1.8499
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3256 - loss: 1.8498 - val_accuracy: 0.3576 - val_loss: 1.8244
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.5738
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3503 - loss: 1.7879  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3469 - loss: 1.8065
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3437 - loss: 1.8162
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3408 - loss: 1.8190
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8203
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8226
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8236
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3326 - loss: 1.8244
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3314 - loss: 1.8251
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 1.8253
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8253
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3303 - loss: 1.8252
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8251
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3298 - loss: 1.8253
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 1.8254
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8254
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3294 - loss: 1.8252
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3294 - loss: 1.8251
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3294 - loss: 1.8249
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3294 - loss: 1.8246
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8241
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 1.8237
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 1.8234
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8231
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8228
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8225
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 1.8222
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8220
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 1.8219
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 1.8219
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 1.8219
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 1.8220
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 1.8221
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3308 - loss: 1.8222
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3308 - loss: 1.8224
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3309 - loss: 1.8225
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 1.8227
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 1.8228
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8229
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8229
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8229
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3314 - loss: 1.8228
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8228
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8228 - val_accuracy: 0.3817 - val_loss: 1.8233
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 2.0627
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3582 - loss: 1.8546  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3544 - loss: 1.8089
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3530 - loss: 1.7930
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7904
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3516 - loss: 1.7903
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3511 - loss: 1.7901
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3509 - loss: 1.7900
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3507 - loss: 1.7898
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7893
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7894
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7899
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3487 - loss: 1.7905
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7908
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3483 - loss: 1.7909
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7914
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3480 - loss: 1.7920
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7924
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3475 - loss: 1.7928
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7933
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3468 - loss: 1.7937
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3467 - loss: 1.7939
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.7941
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 1.7944
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3462 - loss: 1.7947
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3461 - loss: 1.7949
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3460 - loss: 1.7951
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3459 - loss: 1.7955
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3458 - loss: 1.7958
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3457 - loss: 1.7960
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3457 - loss: 1.7963
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7964
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7966
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3455 - loss: 1.7969
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3455 - loss: 1.7971
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3455 - loss: 1.7972
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7973
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7973
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7974
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7974
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7973
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7974
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7975
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7975
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7975 - val_accuracy: 0.3735 - val_loss: 1.8228
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.7821
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3189 - loss: 1.7708  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3233 - loss: 1.7954
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3253 - loss: 1.8024
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8077
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 1.8070
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8025
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 1.7991
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 1.7982
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.7976
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3343 - loss: 1.7972
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3349 - loss: 1.7969
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3354 - loss: 1.7963
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3358 - loss: 1.7959
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3362 - loss: 1.7957
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.7956
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3370 - loss: 1.7952
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3371 - loss: 1.7945
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3374 - loss: 1.7938
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.7929
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3383 - loss: 1.7921
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.7914
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.7906
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.7899
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.7892
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.7887
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 1.7883
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.7879
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3407 - loss: 1.7876
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3409 - loss: 1.7872
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7869
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3412 - loss: 1.7866
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3414 - loss: 1.7864
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.7861
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.7857
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.7854
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3421 - loss: 1.7851
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3423 - loss: 1.7848
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.7846
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.7843
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.7841
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3431 - loss: 1.7839
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.7836
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3434 - loss: 1.7835
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3434 - loss: 1.7834 - val_accuracy: 0.3732 - val_loss: 1.7978
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.4575
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3507 - loss: 1.6854  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3626 - loss: 1.6850
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3680 - loss: 1.6849
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3701 - loss: 1.6890
[1m 140/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3725 - loss: 1.6912
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3727 - loss: 1.6964
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7002
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7033
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7060
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3732 - loss: 1.7076
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3730 - loss: 1.7093
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7109
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7124
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7140
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7155
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7168
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3704 - loss: 1.7183
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7199
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3692 - loss: 1.7215
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7229
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7241
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7251
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7262
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7272
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3673 - loss: 1.7281
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7290
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7298
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7304
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7310
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7317
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7324
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7329
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7334
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7338
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7343
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7346
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7350
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7353
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7357
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7360
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7364
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7366
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7369
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7370 - val_accuracy: 0.3771 - val_loss: 1.7882
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.5000 - loss: 1.4748
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3839 - loss: 1.6485  
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3693 - loss: 1.6684
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3703 - loss: 1.6762
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.6883
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3691 - loss: 1.6960
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7015
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7057
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7087
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7114
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7137
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7153
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7167
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7184
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7203
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7220
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7236
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7247
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7256
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7263
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7268
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7272
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7275
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7279
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7283
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7288
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7292
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7297
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7301
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7305
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3617 - loss: 1.7307
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7309
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7311
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7312
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7312
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7313
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7314
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7315
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7315
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7315
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7316
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7316
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7317
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7317
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7317 - val_accuracy: 0.3648 - val_loss: 1.8217
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 1.7866
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3197 - loss: 1.7180  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3501 - loss: 1.6713
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3540 - loss: 1.6653
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3554 - loss: 1.6669
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3553 - loss: 1.6714
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3550 - loss: 1.6759
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3548 - loss: 1.6800
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.6832
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3547 - loss: 1.6864
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3547 - loss: 1.6893
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3550 - loss: 1.6919
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.6939
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3559 - loss: 1.6958
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.6975
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3564 - loss: 1.6992
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7007
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7018
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7028
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7035
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7040
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7045
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7052
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7056
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7060
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7063
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7066
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7070
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7075
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7078
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7082
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7084
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7087
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7088
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7089
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7090
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7091
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7093
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7094
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7095
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7097
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7098
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7099
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7101
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7101 - val_accuracy: 0.3802 - val_loss: 1.8037
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7770
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3756 - loss: 1.7471  
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7330
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3811 - loss: 1.7228
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3814 - loss: 1.7188
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3819 - loss: 1.7166
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3826 - loss: 1.7143
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3830 - loss: 1.7137
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3832 - loss: 1.7129
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3831 - loss: 1.7121
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3828 - loss: 1.7118
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3824 - loss: 1.7118
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3820 - loss: 1.7119
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3816 - loss: 1.7119
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3811 - loss: 1.7118
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3806 - loss: 1.7119
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3801 - loss: 1.7120
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3796 - loss: 1.7120
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7121
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.7122
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7123
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3778 - loss: 1.7121
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7119
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7117
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7116
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.7113
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3762 - loss: 1.7110
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3760 - loss: 1.7107
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3758 - loss: 1.7104
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3757 - loss: 1.7101
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3756 - loss: 1.7098
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.7096
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.7093
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.7091
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7089
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7087
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7085
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7083
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7081
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7079
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7076
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7074
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7071
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7069
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7069 - val_accuracy: 0.3702 - val_loss: 1.7745

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 1s/step
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:22:35.354440: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:37[0m 1s/step
[1m 46/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m 99/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m158/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 968us/step
[1m216/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 942us/step
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 923us/step
[1m331/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 919us/step
[1m385/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 921us/step
[1m444/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 912us/step
[1m501/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 910us/step
[1m556/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 911us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 968us/step
[1m104/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 980us/step
[1m160/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 950us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 38.65 [%]
Global F1 score (validation) = 36.91 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.21531945 0.23969299 0.15895092 ... 0.01534009 0.10656902 0.0180029 ]
 [0.22824882 0.22576828 0.17738608 ... 0.00187746 0.15287107 0.00797617]
 [0.26070485 0.2689644  0.19598359 ... 0.00209638 0.15138869 0.0137506 ]
 ...
 [0.23672305 0.2048365  0.21563174 ... 0.00066001 0.19009255 0.01455725]
 [0.22575417 0.24187969 0.18248014 ... 0.00292654 0.13517164 0.00698139]
 [0.26353863 0.26863724 0.19680811 ... 0.00175027 0.1575004  0.01780552]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 47.59 [%]
Global accuracy score (test) = 34.86 [%]
Global F1 score (train) = 45.53 [%]
Global F1 score (test) = 33.28 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.19      0.36      0.25       184
 CAMINAR CON MÓVIL O LIBRO       0.25      0.40      0.31       184
       CAMINAR USUAL SPEED       0.07      0.01      0.01       184
            CAMINAR ZIGZAG       0.53      0.57      0.54       184
          DE PIE BARRIENDO       0.35      0.42      0.38       184
   DE PIE DOBLANDO TOALLAS       0.32      0.14      0.19       184
    DE PIE MOVIENDO LIBROS       0.28      0.45      0.35       184
          DE PIE USANDO PC       0.40      0.51      0.45       184
        FASE REPOSO CON K5       0.93      0.62      0.75       184
INCREMENTAL CICLOERGOMETRO       0.72      0.53      0.61       184
           SENTADO LEYENDO       0.28      0.44      0.34       184
         SENTADO USANDO PC       0.23      0.28      0.25       184
      SENTADO VIENDO LA TV       0.17      0.07      0.09       184
   SUBIR Y BAJAR ESCALERAS       0.16      0.04      0.06       184
                    TROTAR       0.39      0.43      0.41       161

                  accuracy                           0.35      2737
                 macro avg       0.35      0.35      0.33      2737
              weighted avg       0.35      0.35      0.33      2737


Accuracy capturado en la ejecución 2: 34.86 [%]
F1-score capturado en la ejecución 2: 33.28 [%]

=== EJECUCIÓN 3 ===

--- TRAIN (ejecución 3) ---

--- TEST (ejecución 3) ---
2025-10-31 15:22:48.606782: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:22:48.617962: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761920568.631197 1649554 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761920568.635402 1649554 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761920568.645247 1649554 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920568.645267 1649554 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920568.645269 1649554 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920568.645270 1649554 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:22:48.648553: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761920571.018236 1649554 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761920574.117360 1649674 service.cc:152] XLA service 0x75eb9801ad40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761920574.117398 1649674 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:22:54.182229: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761920574.618472 1649674 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761920577.249426 1649674 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46:46[0m 5s/step - accuracy: 0.0625 - loss: 3.8519
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0667 - loss: 3.3400    
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0606 - loss: 3.3411
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0637 - loss: 3.3339
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0647 - loss: 3.3357
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0654 - loss: 3.3307
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0660 - loss: 3.3215
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0663 - loss: 3.3128
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0669 - loss: 3.3027
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0676 - loss: 3.2926
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0683 - loss: 3.2833
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0690 - loss: 3.2736
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0699 - loss: 3.2630
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0708 - loss: 3.2534
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0718 - loss: 3.2423
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0728 - loss: 3.2322
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0737 - loss: 3.2237
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0748 - loss: 3.2138
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0760 - loss: 3.2033
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0770 - loss: 3.1936
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0779 - loss: 3.1845
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0788 - loss: 3.1764
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0796 - loss: 3.1686
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0806 - loss: 3.1603
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0815 - loss: 3.1523
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0823 - loss: 3.1448
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0831 - loss: 3.1370
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0839 - loss: 3.1296
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0846 - loss: 3.1230
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0853 - loss: 3.1159
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0859 - loss: 3.1095
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0866 - loss: 3.1027
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0873 - loss: 3.0962
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0880 - loss: 3.0895
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0886 - loss: 3.0836
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0892 - loss: 3.0778
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0899 - loss: 3.0716
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0905 - loss: 3.0661
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0911 - loss: 3.0603
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0917 - loss: 3.0543
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0923 - loss: 3.0489
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0928 - loss: 3.0434
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0934 - loss: 3.0377
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0940 - loss: 3.0323
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0944 - loss: 3.0275
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.0945 - loss: 3.0269
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.0945 - loss: 3.0267 - val_accuracy: 0.2113 - val_loss: 2.2635
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.0625 - loss: 3.1030
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1272 - loss: 2.6974  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1347 - loss: 2.6325
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1407 - loss: 2.6034
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1408 - loss: 2.5891
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1408 - loss: 2.5794
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1412 - loss: 2.5715
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1422 - loss: 2.5640
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1432 - loss: 2.5579
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1441 - loss: 2.5530
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1449 - loss: 2.5489
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1454 - loss: 2.5455
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1456 - loss: 2.5431
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1456 - loss: 2.5410
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1457 - loss: 2.5385
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1459 - loss: 2.5355
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1461 - loss: 2.5330
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1463 - loss: 2.5305
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1465 - loss: 2.5281
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1467 - loss: 2.5256
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1469 - loss: 2.5231
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1470 - loss: 2.5210
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1472 - loss: 2.5190
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1474 - loss: 2.5171
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1475 - loss: 2.5155
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1477 - loss: 2.5139
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1480 - loss: 2.5122
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5107
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1483 - loss: 2.5091
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1485 - loss: 2.5075
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1487 - loss: 2.5060
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1488 - loss: 2.5045
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1490 - loss: 2.5030
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1492 - loss: 2.5015
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1494 - loss: 2.5002
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1496 - loss: 2.4988
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1498 - loss: 2.4976
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1500 - loss: 2.4964
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1501 - loss: 2.4951
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1503 - loss: 2.4940
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1505 - loss: 2.4929
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1507 - loss: 2.4917
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1508 - loss: 2.4906
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1510 - loss: 2.4895
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1511 - loss: 2.4889 - val_accuracy: 0.2076 - val_loss: 2.1647
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0403
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1651 - loss: 2.4085  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1636 - loss: 2.3959
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1611 - loss: 2.3871
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1604 - loss: 2.3840
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1597 - loss: 2.3806
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1590 - loss: 2.3779
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1583 - loss: 2.3759
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1581 - loss: 2.3741
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1584 - loss: 2.3726
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1592 - loss: 2.3712
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1599 - loss: 2.3698
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1605 - loss: 2.3684
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1611 - loss: 2.3673
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1616 - loss: 2.3661
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1621 - loss: 2.3650
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1625 - loss: 2.3644
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1629 - loss: 2.3635
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1633 - loss: 2.3627
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1637 - loss: 2.3620
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1641 - loss: 2.3614
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1644 - loss: 2.3608
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3602
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1651 - loss: 2.3597
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1653 - loss: 2.3592
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1655 - loss: 2.3586
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1658 - loss: 2.3580
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1660 - loss: 2.3573
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1662 - loss: 2.3567
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1665 - loss: 2.3562
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1667 - loss: 2.3557
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3552
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1670 - loss: 2.3547
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1672 - loss: 2.3541
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1673 - loss: 2.3536
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1674 - loss: 2.3530
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1676 - loss: 2.3524
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1677 - loss: 2.3519
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1678 - loss: 2.3514
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3508
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3502
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1683 - loss: 2.3496
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3491
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1685 - loss: 2.3486
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1685 - loss: 2.3482 - val_accuracy: 0.2246 - val_loss: 2.1068
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.2545
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1483 - loss: 2.3340  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1555 - loss: 2.3095
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1596 - loss: 2.2983
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1619 - loss: 2.2953
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1625 - loss: 2.2935
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1635 - loss: 2.2908
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1645 - loss: 2.2887
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1657 - loss: 2.2871
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1669 - loss: 2.2863
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1680 - loss: 2.2856
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1691 - loss: 2.2852
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1701 - loss: 2.2849
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.2843
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1719 - loss: 2.2837
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1727 - loss: 2.2829
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.2820
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1739 - loss: 2.2812
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1744 - loss: 2.2805
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1748 - loss: 2.2797
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1753 - loss: 2.2788
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1757 - loss: 2.2780
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1762 - loss: 2.2771
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1765 - loss: 2.2762
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1770 - loss: 2.2753
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1774 - loss: 2.2744
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1778 - loss: 2.2736
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.2728
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1783 - loss: 2.2722
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1785 - loss: 2.2715
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1787 - loss: 2.2708
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1790 - loss: 2.2701
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.2693
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.2686
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.2679
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.2673
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1800 - loss: 2.2667
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.2661
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.2655
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1805 - loss: 2.2649
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1807 - loss: 2.2643
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1809 - loss: 2.2637
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1810 - loss: 2.2632
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1812 - loss: 2.2627
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1813 - loss: 2.2624 - val_accuracy: 0.2098 - val_loss: 2.0547
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.2500 - loss: 2.1937
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2258 - loss: 2.1807  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2080 - loss: 2.2007
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2061 - loss: 2.2034
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2052 - loss: 2.2052
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2051 - loss: 2.2056
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2050 - loss: 2.2063
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2051 - loss: 2.2058
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2051 - loss: 2.2048
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2040
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2039 - loss: 2.2036
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2036 - loss: 2.2032
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2033 - loss: 2.2027
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2030 - loss: 2.2022
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2027 - loss: 2.2020
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2023 - loss: 2.2018
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.2016
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2019 - loss: 2.2017
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2016 - loss: 2.2020
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2014 - loss: 2.2021
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2012 - loss: 2.2022
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.2021
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2008 - loss: 2.2020
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2006 - loss: 2.2018
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2003 - loss: 2.2017
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2001 - loss: 2.2016
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1999 - loss: 2.2015
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1998 - loss: 2.2013
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1997 - loss: 2.2012
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1996 - loss: 2.2009
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1995 - loss: 2.2007
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1995 - loss: 2.2005
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1994 - loss: 2.2003
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1993 - loss: 2.2001
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1993 - loss: 2.2000
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1992 - loss: 2.1999
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1992 - loss: 2.1997
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1991 - loss: 2.1996
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1990 - loss: 2.1996
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1990 - loss: 2.1995
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1990 - loss: 2.1994
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1989 - loss: 2.1993
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1989 - loss: 2.1992
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1989 - loss: 2.1991
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1989 - loss: 2.1991 - val_accuracy: 0.2535 - val_loss: 2.0226
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4410
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1921 - loss: 2.3003  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2054 - loss: 2.2688
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2126 - loss: 2.2417
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2136 - loss: 2.2302
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2144 - loss: 2.2230
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2145 - loss: 2.2178
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2149 - loss: 2.2130
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2154 - loss: 2.2099
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2158 - loss: 2.2062
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2162 - loss: 2.2023
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2165 - loss: 2.1992
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2167 - loss: 2.1964
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2171 - loss: 2.1940
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2174 - loss: 2.1919
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2177 - loss: 2.1899
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2179 - loss: 2.1881
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2181 - loss: 2.1868
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2182 - loss: 2.1855
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2184 - loss: 2.1841
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2184 - loss: 2.1830
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1818
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1805
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1795
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1786
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1778
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1769
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1762
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1755
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1748
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1742
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1736
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1730
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1724
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1719
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1713
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1707
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1701
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.1697
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.1693
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.1689
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.1685
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.1681
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.1678
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2187 - loss: 2.1676 - val_accuracy: 0.2834 - val_loss: 1.9629
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3021
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2494 - loss: 2.1240  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2505 - loss: 2.1113
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2499 - loss: 2.1049
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2495 - loss: 2.1019
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2500 - loss: 2.1005
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2494 - loss: 2.1012
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2487 - loss: 2.1020
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2483 - loss: 2.1025
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.1028
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2476 - loss: 2.1030
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2473 - loss: 2.1030
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.1034
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2466 - loss: 2.1042
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1053
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2454 - loss: 2.1064
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2449 - loss: 2.1073
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2444 - loss: 2.1080
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2439 - loss: 2.1087
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2435 - loss: 2.1092
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.1095
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.1097
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.1099
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2423 - loss: 2.1099
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2421 - loss: 2.1100
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2418 - loss: 2.1100
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.1101
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2415 - loss: 2.1101
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.1101
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.1099
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.1098
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.1096
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.1093
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.1091
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.1088
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.1086
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2415 - loss: 2.1083
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2415 - loss: 2.1081
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2415 - loss: 2.1079
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.1078
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.1076
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.1074
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2417 - loss: 2.1072
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2417 - loss: 2.1070
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2418 - loss: 2.1068
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2419 - loss: 2.1066 - val_accuracy: 0.2577 - val_loss: 1.9568
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1875 - loss: 1.7217
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2549 - loss: 1.9769  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2440 - loss: 2.0243
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2425 - loss: 2.0364
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2448 - loss: 2.0412
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2467 - loss: 2.0463
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2486 - loss: 2.0499
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2506 - loss: 2.0514
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2519 - loss: 2.0521
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2525 - loss: 2.0538
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2530 - loss: 2.0551
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2535 - loss: 2.0569
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2537 - loss: 2.0581
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.0593
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2542 - loss: 2.0600
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.0604
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.0609
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.0612
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2547 - loss: 2.0612
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2548 - loss: 2.0611
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2549 - loss: 2.0610
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2550 - loss: 2.0608
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2552 - loss: 2.0603
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2555 - loss: 2.0598
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2559 - loss: 2.0592
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2562 - loss: 2.0587
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2565 - loss: 2.0583
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2567 - loss: 2.0578
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2570 - loss: 2.0575
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2573 - loss: 2.0571
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.0568
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.0563
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2578 - loss: 2.0559
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2580 - loss: 2.0555
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.0551
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.0547
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2585 - loss: 2.0543
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.0539
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.0535
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.0532
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2592 - loss: 2.0528
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 2.0524
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.0520
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.0516
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.0511
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2601 - loss: 2.0509 - val_accuracy: 0.3190 - val_loss: 1.8658
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.5000 - loss: 2.2988
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0229  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3190 - loss: 1.9969
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3130 - loss: 1.9935
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3068 - loss: 1.9953
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3025 - loss: 1.9961
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 1.9994
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 2.0013
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 2.0030
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2907 - loss: 2.0037
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2891 - loss: 2.0047
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2878 - loss: 2.0052
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2869 - loss: 2.0055
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.0057
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2853 - loss: 2.0055
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.0050
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.0047
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.0047
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 2.0046
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 2.0047
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2833 - loss: 2.0048
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2831 - loss: 2.0049
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2829 - loss: 2.0051
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 2.0051
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.0051
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2826 - loss: 2.0050
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.0048
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.0046
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 2.0043
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 2.0040
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.0037
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.0033
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.0029
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 2.0025
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.0021
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.0018
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2836 - loss: 2.0014
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.0011
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2839 - loss: 2.0007
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2841 - loss: 2.0003
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2842 - loss: 1.9999
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2844 - loss: 1.9994
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 1.9989
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 1.9984
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 1.9980
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2849 - loss: 1.9978 - val_accuracy: 0.3439 - val_loss: 1.8039
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 2.3906
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3181 - loss: 1.9394  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3184 - loss: 1.9276
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3204 - loss: 1.9228
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3180 - loss: 1.9265
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3171 - loss: 1.9296
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3165 - loss: 1.9315
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 1.9325
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9329
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 1.9325
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 1.9320
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9312
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 1.9309
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 1.9301
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3120 - loss: 1.9293
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 1.9283
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 1.9276
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 1.9270
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3105 - loss: 1.9265
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 1.9262
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 1.9258
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 1.9254
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 1.9251
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 1.9248
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3100 - loss: 1.9245
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3100 - loss: 1.9243
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 1.9242
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 1.9242
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 1.9241
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3095 - loss: 1.9241
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9240
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 1.9240
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3090 - loss: 1.9240
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 1.9241
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 1.9242
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3085 - loss: 1.9243
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3084 - loss: 1.9244
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3082 - loss: 1.9245
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3081 - loss: 1.9245
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3079 - loss: 1.9246
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3078 - loss: 1.9248
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3077 - loss: 1.9249
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3076 - loss: 1.9250
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 1.9252
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3074 - loss: 1.9252
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3073 - loss: 1.9253 - val_accuracy: 0.3412 - val_loss: 1.7725
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1875 - loss: 1.9150
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8653  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3215 - loss: 1.8817
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8894
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8920
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8954
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8990
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 1.9019
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3198 - loss: 1.9043
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 1.9066
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 1.9084
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 1.9092
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 1.9091
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 1.9089
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 1.9085
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 1.9077
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3198 - loss: 1.9069
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 1.9057
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 1.9048
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 1.9041
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 1.9032
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 1.9025
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 1.9020
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 1.9014
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 1.9009
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 1.9005
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 1.9001
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8998
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8994
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8991
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8987
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8983
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8980
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3187 - loss: 1.8977
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3187 - loss: 1.8974
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3186 - loss: 1.8972
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3186 - loss: 1.8969
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8967
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8965
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3184 - loss: 1.8962
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8960
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8958
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8955
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8953
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8950 - val_accuracy: 0.3582 - val_loss: 1.7548
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.1875 - loss: 1.8284
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2626 - loss: 1.9267  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2922 - loss: 1.9180
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3032 - loss: 1.9190
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3078 - loss: 1.9159
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3092 - loss: 1.9156
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3105 - loss: 1.9139
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 1.9115
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 1.9088
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3121 - loss: 1.9062
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 1.9038
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 1.9021
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.9000
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 1.8983
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 1.8963
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 1.8947
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 1.8933
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 1.8920
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 1.8908
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 1.8894
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3154 - loss: 1.8879
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 1.8866
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3160 - loss: 1.8854
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3163 - loss: 1.8844
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8836
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8827
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8815
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8804
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 1.8794
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3184 - loss: 1.8785
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3187 - loss: 1.8777
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8770
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8763
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 1.8757
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8751
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 1.8745
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 1.8739
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8734
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 1.8729
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 1.8724
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 1.8719
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 1.8714
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3210 - loss: 1.8708
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3212 - loss: 1.8703
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3213 - loss: 1.8698 - val_accuracy: 0.3478 - val_loss: 1.7568
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.7017
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3278 - loss: 1.8477  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3250 - loss: 1.8594
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3251 - loss: 1.8574
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3277 - loss: 1.8495
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3296 - loss: 1.8436
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8405
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8380
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8343
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8311
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8285
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3324 - loss: 1.8272
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 1.8256
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3330 - loss: 1.8239
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8222
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8211
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3341 - loss: 1.8202
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8200
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3343 - loss: 1.8199
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8199
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8199
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8198
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8196
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8194
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8192
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8190
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3348 - loss: 1.8189
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3350 - loss: 1.8187
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3351 - loss: 1.8184
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3352 - loss: 1.8182
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8180
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8178
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3356 - loss: 1.8176
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8174
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3358 - loss: 1.8172
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8170
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8168
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8167
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8166
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8166
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8166
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8165
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8165
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8165
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8164
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8164 - val_accuracy: 0.3747 - val_loss: 1.7183
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.7988
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3520 - loss: 1.8520  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3515 - loss: 1.8544
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3519 - loss: 1.8473
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3525 - loss: 1.8399
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3529 - loss: 1.8331
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3533 - loss: 1.8281
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3535 - loss: 1.8241
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3535 - loss: 1.8210
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3537 - loss: 1.8179
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.8149
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3557 - loss: 1.8121
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3564 - loss: 1.8100
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3569 - loss: 1.8080
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.8058
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.8040
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3578 - loss: 1.8026
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.8010
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7997
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7987
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7980
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7971
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7967
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7964
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7960
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7958
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7956
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7955
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7956
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7956
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7955
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7953
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7951
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7949
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7947
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7946
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7944
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7942
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7941
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7940
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7938
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7937
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7936
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7935
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7934 - val_accuracy: 0.3534 - val_loss: 1.7546
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9142
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7705  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7578
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7533
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7529
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7536
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7562
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7567
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7576
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7579
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7590
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7599
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7605
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7609
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7612
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7618
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7622
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7625
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3551 - loss: 1.7628
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7633
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7636
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7640
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3540 - loss: 1.7644
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7645
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7647
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7649
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7651
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7654
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7656
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7659
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7661
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7662
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7664
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7664
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7664
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7664
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7664
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7663
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7662
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7661
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7660
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3540 - loss: 1.7659
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3540 - loss: 1.7658
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3541 - loss: 1.7656
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7655
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7655 - val_accuracy: 0.3850 - val_loss: 1.7380
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.9028
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3445 - loss: 1.7724  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7113
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3749 - loss: 1.6888
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3748 - loss: 1.6818
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3741 - loss: 1.6818
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3736 - loss: 1.6838
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3729 - loss: 1.6879
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3725 - loss: 1.6911
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3721 - loss: 1.6939
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.6963
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.6980
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3705 - loss: 1.6997
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3700 - loss: 1.7016
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7030
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3691 - loss: 1.7043
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7057
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3680 - loss: 1.7074
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7090
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7104
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7118
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7133
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7147
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7160
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7173
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7185
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7197
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7207
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7216
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7224
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7232
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7239
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7246
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7251
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7258
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7264
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7269
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7274
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7278
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7282
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7286
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7289
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7292
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7296
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7298
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7299 - val_accuracy: 0.3726 - val_loss: 1.7303
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1875 - loss: 1.8558
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2913 - loss: 1.8663  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3266 - loss: 1.8028
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3383 - loss: 1.7810
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3441 - loss: 1.7700
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3478 - loss: 1.7632
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3513 - loss: 1.7565
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7524
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7509
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7503
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7494
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7482
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7466
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7452
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7438
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7427
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7417
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7411
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7406
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7401
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7395
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7389
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7385
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7381
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7376
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7371
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7366
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7361
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7356
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7352
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3673 - loss: 1.7347
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7342
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7338
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7334
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7329
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7324
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7320
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7316
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3691 - loss: 1.7312
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7308
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7303
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7299
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7295
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7293
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7292 - val_accuracy: 0.3647 - val_loss: 1.7368
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.6829
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4214 - loss: 1.7056  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3993 - loss: 1.7200
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3928 - loss: 1.7173
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3874 - loss: 1.7139
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3842 - loss: 1.7122
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3828 - loss: 1.7100
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3818 - loss: 1.7102
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3818 - loss: 1.7098
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3817 - loss: 1.7103
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3817 - loss: 1.7106
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3816 - loss: 1.7108
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3816 - loss: 1.7110
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3816 - loss: 1.7113
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3816 - loss: 1.7111
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3817 - loss: 1.7107
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3817 - loss: 1.7103
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3816 - loss: 1.7099
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3815 - loss: 1.7094
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3814 - loss: 1.7089
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3812 - loss: 1.7086
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3811 - loss: 1.7082
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3810 - loss: 1.7078
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3809 - loss: 1.7076
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3809 - loss: 1.7073
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3808 - loss: 1.7070
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3807 - loss: 1.7067
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3807 - loss: 1.7064
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3806 - loss: 1.7062
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3805 - loss: 1.7059
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3805 - loss: 1.7056
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3805 - loss: 1.7053
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3804 - loss: 1.7050
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3804 - loss: 1.7048
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3803 - loss: 1.7046
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3802 - loss: 1.7045
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3802 - loss: 1.7044
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3801 - loss: 1.7042
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3800 - loss: 1.7041
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3799 - loss: 1.7040
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3798 - loss: 1.7040
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3797 - loss: 1.7039
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3796 - loss: 1.7038
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.7038
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3794 - loss: 1.7038
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3794 - loss: 1.7037 - val_accuracy: 0.3682 - val_loss: 1.7373

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 1s/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:23:53.111196: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:35[0m 1s/step
[1m 45/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m 98/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m158/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 964us/step
[1m213/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 950us/step
[1m271/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 934us/step
[1m327/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 930us/step
[1m370/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 959us/step
[1m426/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 950us/step
[1m476/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 957us/step
[1m521/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 971us/step
[1m574/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 972us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 968us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 991us/step
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 929us/step
[1m165/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 930us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 37.02 [%]
Global F1 score (validation) = 34.18 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.2126901  0.21951    0.18777454 ... 0.01216711 0.13493821 0.03994252]
 [0.2005512  0.209968   0.2014169  ... 0.00313761 0.1502576  0.01225634]
 [0.2532596  0.22435978 0.20995077 ... 0.00533195 0.14097193 0.04405815]
 ...
 [0.16807488 0.22770885 0.15059389 ... 0.00831113 0.1037569  0.00943031]
 [0.1950498  0.22251013 0.18006395 ... 0.00313084 0.13461484 0.01032622]
 [0.22924449 0.2104054  0.21695092 ... 0.00258983 0.15326563 0.01569312]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.27 [%]
Global accuracy score (test) = 34.45 [%]
Global F1 score (train) = 43.81 [%]
Global F1 score (test) = 32.76 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.16      0.17      0.16       184
 CAMINAR CON MÓVIL O LIBRO       0.18      0.39      0.24       184
       CAMINAR USUAL SPEED       0.16      0.08      0.10       184
            CAMINAR ZIGZAG       0.45      0.58      0.51       184
          DE PIE BARRIENDO       0.30      0.33      0.31       184
   DE PIE DOBLANDO TOALLAS       0.38      0.18      0.24       184
    DE PIE MOVIENDO LIBROS       0.33      0.55      0.41       184
          DE PIE USANDO PC       0.42      0.51      0.46       184
        FASE REPOSO CON K5       0.84      0.76      0.80       184
INCREMENTAL CICLOERGOMETRO       0.82      0.58      0.68       184
           SENTADO LEYENDO       0.26      0.46      0.33       184
         SENTADO USANDO PC       0.15      0.12      0.13       184
      SENTADO VIENDO LA TV       0.27      0.11      0.16       184
   SUBIR Y BAJAR ESCALERAS       0.00      0.00      0.00       184
                    TROTAR       0.37      0.37      0.37       161

                  accuracy                           0.34      2737
                 macro avg       0.34      0.34      0.33      2737
              weighted avg       0.34      0.34      0.33      2737


Accuracy capturado en la ejecución 3: 34.45 [%]
F1-score capturado en la ejecución 3: 32.76 [%]

=== EJECUCIÓN 4 ===

--- TRAIN (ejecución 4) ---

--- TEST (ejecución 4) ---
2025-10-31 15:24:06.295676: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:24:06.307010: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761920646.320182 1652687 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761920646.324434 1652687 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761920646.334232 1652687 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920646.334252 1652687 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920646.334254 1652687 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920646.334256 1652687 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:24:06.337529: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761920648.683014 1652687 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761920651.796069 1652793 service.cc:152] XLA service 0x790248006cd0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761920651.796112 1652793 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:24:11.861290: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761920652.300727 1652793 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761920654.952063 1652793 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46:52[0m 5s/step - accuracy: 0.0625 - loss: 3.1424
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0725 - loss: 3.2620    
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0804 - loss: 3.2445
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0835 - loss: 3.2466
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0849 - loss: 3.2385
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0858 - loss: 3.2255
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0866 - loss: 3.2130
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0877 - loss: 3.2016
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0885 - loss: 3.1912
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0895 - loss: 3.1798
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0904 - loss: 3.1689
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0917 - loss: 3.1572
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0930 - loss: 3.1468
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0942 - loss: 3.1368
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0951 - loss: 3.1280
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0961 - loss: 3.1186
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0969 - loss: 3.1099
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0977 - loss: 3.1016
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0983 - loss: 3.0940
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0990 - loss: 3.0869
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0996 - loss: 3.0795
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1002 - loss: 3.0735
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1008 - loss: 3.0667
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1014 - loss: 3.0605
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1020 - loss: 3.0540
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1027 - loss: 3.0475
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1033 - loss: 3.0412
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1038 - loss: 3.0353
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1043 - loss: 3.0293
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1048 - loss: 3.0239
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1052 - loss: 3.0187
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1056 - loss: 3.0130
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1060 - loss: 3.0079
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1063 - loss: 3.0031
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1067 - loss: 2.9984
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1070 - loss: 2.9934
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1074 - loss: 2.9884
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1077 - loss: 2.9837
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1081 - loss: 2.9786
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1085 - loss: 2.9739
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1088 - loss: 2.9692
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1091 - loss: 2.9657
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1094 - loss: 2.9616
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1097 - loss: 2.9569
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1100 - loss: 2.9537
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1100 - loss: 2.9535 - val_accuracy: 0.1722 - val_loss: 2.2977
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.5052
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1754 - loss: 2.4922  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1649 - loss: 2.5024
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1589 - loss: 2.5087
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1562 - loss: 2.5096
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1544 - loss: 2.5086
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1533 - loss: 2.5088
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1527 - loss: 2.5087
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1523 - loss: 2.5090
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1521 - loss: 2.5090
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1518 - loss: 2.5090
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1516 - loss: 2.5086
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1514 - loss: 2.5081
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1512 - loss: 2.5073
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1512 - loss: 2.5062
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1510 - loss: 2.5055
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1509 - loss: 2.5049
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1508 - loss: 2.5042
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1508 - loss: 2.5035
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1507 - loss: 2.5027
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1507 - loss: 2.5018
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1507 - loss: 2.5008
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1508 - loss: 2.4998
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1509 - loss: 2.4987
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1509 - loss: 2.4979
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1509 - loss: 2.4970
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1510 - loss: 2.4962
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1510 - loss: 2.4954
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1511 - loss: 2.4946
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1511 - loss: 2.4939
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1512 - loss: 2.4930
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1512 - loss: 2.4922
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1513 - loss: 2.4912
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1514 - loss: 2.4902
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1515 - loss: 2.4892
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1516 - loss: 2.4882
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1517 - loss: 2.4874
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1518 - loss: 2.4864
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1519 - loss: 2.4854
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1521 - loss: 2.4845
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1522 - loss: 2.4835
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1523 - loss: 2.4827
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1524 - loss: 2.4817
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1525 - loss: 2.4808
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1526 - loss: 2.4799 - val_accuracy: 0.2015 - val_loss: 2.1758
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3258
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1713 - loss: 2.3756  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1697 - loss: 2.3727
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1671 - loss: 2.3828
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1667 - loss: 2.3882
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1666 - loss: 2.3891
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1667 - loss: 2.3880
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1667 - loss: 2.3858
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1672 - loss: 2.3820
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1679 - loss: 2.3773
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1686 - loss: 2.3737
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3705
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1695 - loss: 2.3684
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1698 - loss: 2.3669
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1701 - loss: 2.3652
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1705 - loss: 2.3637
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1708 - loss: 2.3622
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3607
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3591
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1717 - loss: 2.3576
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3562
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1719 - loss: 2.3550
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1720 - loss: 2.3539
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1721 - loss: 2.3526
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1722 - loss: 2.3516
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1723 - loss: 2.3506
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1725 - loss: 2.3497
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1726 - loss: 2.3488
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3480
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3473
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1728 - loss: 2.3465
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1729 - loss: 2.3456
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1730 - loss: 2.3449
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1730 - loss: 2.3442
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1730 - loss: 2.3435
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1731 - loss: 2.3428
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1732 - loss: 2.3422
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1732 - loss: 2.3415
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1733 - loss: 2.3409
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1735 - loss: 2.3402
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1736 - loss: 2.3395
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1737 - loss: 2.3389
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1738 - loss: 2.3382
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1739 - loss: 2.3374
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1740 - loss: 2.3367
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1741 - loss: 2.3365 - val_accuracy: 0.2302 - val_loss: 2.1141
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 2.2020
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2230 - loss: 2.2309  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2086 - loss: 2.2579
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2043 - loss: 2.2671
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2025 - loss: 2.2671
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1999 - loss: 2.2673
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1976 - loss: 2.2666
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1956 - loss: 2.2669
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1940 - loss: 2.2665
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1927 - loss: 2.2655
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1917 - loss: 2.2654
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1909 - loss: 2.2652
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1903 - loss: 2.2652
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1898 - loss: 2.2653
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1894 - loss: 2.2653
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1891 - loss: 2.2652
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1890 - loss: 2.2651
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1889 - loss: 2.2649
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1888 - loss: 2.2648
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1886 - loss: 2.2647
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1884 - loss: 2.2646
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1884 - loss: 2.2645
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1882 - loss: 2.2644
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1882 - loss: 2.2641
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1881 - loss: 2.2638
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2635
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2631
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2627
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2623
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.2619
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1878 - loss: 2.2616
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1877 - loss: 2.2613
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1876 - loss: 2.2610
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1876 - loss: 2.2606
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2602
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2598
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2594
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1874 - loss: 2.2591
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1874 - loss: 2.2588
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1874 - loss: 2.2584
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1874 - loss: 2.2580
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2576
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2571
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2568
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2565 - val_accuracy: 0.2411 - val_loss: 2.0535
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.0277
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2056 - loss: 2.2644  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2041 - loss: 2.2525
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2006 - loss: 2.2468
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1982 - loss: 2.2434
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1961 - loss: 2.2373
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1946 - loss: 2.2333
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1934 - loss: 2.2307
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1928 - loss: 2.2281
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1923 - loss: 2.2261
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1920 - loss: 2.2239
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1920 - loss: 2.2219
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1920 - loss: 2.2205
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1919 - loss: 2.2193
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1919 - loss: 2.2185
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1919 - loss: 2.2178
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1921 - loss: 2.2169
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1923 - loss: 2.2161
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1925 - loss: 2.2154
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1926 - loss: 2.2148
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1928 - loss: 2.2142
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1930 - loss: 2.2135
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1932 - loss: 2.2129
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1934 - loss: 2.2123
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1937 - loss: 2.2117
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1939 - loss: 2.2111
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1943 - loss: 2.2103
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1946 - loss: 2.2096
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1949 - loss: 2.2088
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1952 - loss: 2.2081
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1955 - loss: 2.2075
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1957 - loss: 2.2069
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1960 - loss: 2.2064
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1962 - loss: 2.2058
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1965 - loss: 2.2052
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1967 - loss: 2.2046
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1970 - loss: 2.2039
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1973 - loss: 2.2033
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1975 - loss: 2.2027
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1978 - loss: 2.2021
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1980 - loss: 2.2016
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.2010
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1986 - loss: 2.2004
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1988 - loss: 2.1999
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1990 - loss: 2.1994
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1991 - loss: 2.1992 - val_accuracy: 0.3051 - val_loss: 1.9704
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.8662
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3089 - loss: 1.9825  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2865 - loss: 2.0313
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2790 - loss: 2.0508
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0645
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2669 - loss: 2.0705
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0738
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2594 - loss: 2.0777
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2567 - loss: 2.0821
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.0860
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2528 - loss: 2.0898
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0925
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2506 - loss: 2.0944
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.0961
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2494 - loss: 2.0973
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.0983
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2485 - loss: 2.0990
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2481 - loss: 2.0995
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.0998
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2476 - loss: 2.0999
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2473 - loss: 2.1000
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2471 - loss: 2.0999
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.0998
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2469 - loss: 2.0997
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2469 - loss: 2.0995
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.0993
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.0993
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2467 - loss: 2.0992
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2467 - loss: 2.0993
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.0994
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.0994
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.0994
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2463 - loss: 2.0994
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2463 - loss: 2.0994
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2462 - loss: 2.0994
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.0993
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.0993
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.0993
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.0992
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.0992
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.0991
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.0991
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.0990
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.0990
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.0989
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2460 - loss: 2.0989 - val_accuracy: 0.3271 - val_loss: 1.9097
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0324
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2746 - loss: 2.1553  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2696 - loss: 2.1401
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2656 - loss: 2.1273
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2640 - loss: 2.1151
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2634 - loss: 2.1073
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2636 - loss: 2.0975
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0897
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.0842
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 2.0799
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0767
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2639 - loss: 2.0733
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2639 - loss: 2.0711
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0696
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.0683
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2635 - loss: 2.0672
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0663
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0656
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0650
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2632 - loss: 2.0644
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0637
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0633
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0629
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2628 - loss: 2.0625
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2627 - loss: 2.0624
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2626 - loss: 2.0621
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2625 - loss: 2.0619
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2624 - loss: 2.0616
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2623 - loss: 2.0613
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2622 - loss: 2.0609
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2621 - loss: 2.0606
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2620 - loss: 2.0603
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0600
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0597
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0594
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0590
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0586
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0583
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0580
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0576
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0572
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0569
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0566
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0563
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0559
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0558 - val_accuracy: 0.3186 - val_loss: 1.8635
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.1250 - loss: 1.9946
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2687 - loss: 1.9182  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2694 - loss: 1.9421
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2693 - loss: 1.9590
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2667 - loss: 1.9761
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2644 - loss: 1.9913
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2627 - loss: 2.0003
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2620 - loss: 2.0050
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0074
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2623 - loss: 2.0089
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0092
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0092
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2646 - loss: 2.0091
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2653 - loss: 2.0088
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2660 - loss: 2.0083
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2668 - loss: 2.0077
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.0071
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2682 - loss: 2.0064
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2690 - loss: 2.0055
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2697 - loss: 2.0047
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.0043
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2708 - loss: 2.0042
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0041
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0038
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2721 - loss: 2.0036
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.0034
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 2.0031
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2733 - loss: 2.0028
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2736 - loss: 2.0026
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0023
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2743 - loss: 2.0020
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2747 - loss: 2.0016
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2750 - loss: 2.0012
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2752 - loss: 2.0008
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2755 - loss: 2.0005
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2756 - loss: 2.0002
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2758 - loss: 1.9999
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2761 - loss: 1.9995
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2763 - loss: 1.9990
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2765 - loss: 1.9986
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 1.9982
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 1.9979
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 1.9975
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 1.9971
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 1.9967
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2775 - loss: 1.9965 - val_accuracy: 0.3552 - val_loss: 1.8146
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.9813
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2449 - loss: 2.1245  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2585 - loss: 2.0742
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2647 - loss: 2.0488
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2683 - loss: 2.0290
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2712 - loss: 2.0166
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2727 - loss: 2.0090
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2747 - loss: 2.0014
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2766 - loss: 1.9951
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 1.9906
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2787 - loss: 1.9864
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 1.9836
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9811
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 1.9790
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 1.9771
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 1.9753
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9736
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 1.9717
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2833 - loss: 1.9699
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 1.9680
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 1.9664
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 1.9650
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2856 - loss: 1.9637
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 1.9624
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 1.9613
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2870 - loss: 1.9602
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2875 - loss: 1.9591
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2880 - loss: 1.9582
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2884 - loss: 1.9572
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2888 - loss: 1.9563
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2892 - loss: 1.9555
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2896 - loss: 1.9546
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2900 - loss: 1.9538
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2903 - loss: 1.9531
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2906 - loss: 1.9525
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2909 - loss: 1.9519
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2912 - loss: 1.9513
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 1.9508
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9502
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 1.9497
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 1.9492
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 1.9487
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9482
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 1.9478
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 1.9474
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2930 - loss: 1.9474 - val_accuracy: 0.3378 - val_loss: 1.8102
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9191
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2918 - loss: 1.9565  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9142
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3070 - loss: 1.9014
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3079 - loss: 1.9010
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 1.8996
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 1.8973
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 1.8957
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8946
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3121 - loss: 1.8941
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 1.8937
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.8934
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.8930
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 1.8930
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 1.8933
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.8938
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.8943
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 1.8948
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 1.8950
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 1.8952
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 1.8954
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 1.8955
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 1.8956
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 1.8957
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 1.8958
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 1.8960
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 1.8963
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 1.8966
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 1.8968
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 1.8971
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 1.8975
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8978
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 1.8980
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 1.8983
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8985
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8987
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8989
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8990
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8992
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8993
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8994
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8994
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8995
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8995
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8996
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8996 - val_accuracy: 0.3711 - val_loss: 1.7658
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9972
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8771  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8906
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3333 - loss: 1.8967
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3318 - loss: 1.8983
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3297 - loss: 1.8997
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3272 - loss: 1.9003
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 1.9014
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 1.9020
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 1.9016
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3223 - loss: 1.9014
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3220 - loss: 1.9004
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 1.8991
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 1.8980
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 1.8968
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 1.8955
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 1.8946
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 1.8940
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 1.8935
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3221 - loss: 1.8926
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 1.8920
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 1.8915
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3223 - loss: 1.8910
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 1.8905
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3225 - loss: 1.8901
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 1.8897
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 1.8894
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.8890
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.8886
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 1.8882
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3228 - loss: 1.8877
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 1.8871
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 1.8865
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 1.8859
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 1.8854
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 1.8848
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 1.8842
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 1.8837
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 1.8833
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 1.8829
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 1.8824
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 1.8821
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8818
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8814
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8810
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3242 - loss: 1.8807 - val_accuracy: 0.3504 - val_loss: 1.7548
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.6184
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2724 - loss: 1.8977  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2763 - loss: 1.9163
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2843 - loss: 1.9125
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2899 - loss: 1.9098
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9107
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9120
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 1.9127
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3032 - loss: 1.9112
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9083
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3062 - loss: 1.9066
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 1.9051
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3078 - loss: 1.9035
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3085 - loss: 1.9015
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 1.8992
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 1.8970
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 1.8948
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8927
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8908
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 1.8891
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 1.8877
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 1.8865
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.8850
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8837
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 1.8825
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 1.8813
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 1.8801
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3147 - loss: 1.8791
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3150 - loss: 1.8781
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.8771
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 1.8762
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3157 - loss: 1.8753
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3158 - loss: 1.8745
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3160 - loss: 1.8738
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3163 - loss: 1.8731
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8723
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8716
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8710
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8702
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8694
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8687
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8680
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8671
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3187 - loss: 1.8665
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8658
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8655 - val_accuracy: 0.3449 - val_loss: 1.7786
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.5790
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3956 - loss: 1.7254  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7625
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7731
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7852
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3514 - loss: 1.7904
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7947
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7987
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.8026
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3453 - loss: 1.8052
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.8076
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8098
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8123
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3408 - loss: 1.8141
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8160
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8174
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8185
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8194
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8201
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.8209
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8214
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8217
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8220
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8223
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8225
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8226
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8226
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8226
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8226
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8227
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8227
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8228
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8227
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8226
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8224
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8223
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8222
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8220
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8219
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8218
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8217
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8216
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8214
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8213
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8211 - val_accuracy: 0.3674 - val_loss: 1.7692
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0329
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3540 - loss: 1.7702  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7595
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3555 - loss: 1.7684
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7774
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7842
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3514 - loss: 1.7880
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3509 - loss: 1.7884
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3501 - loss: 1.7901
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7917
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7931
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3490 - loss: 1.7938
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3490 - loss: 1.7948
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3490 - loss: 1.7951
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.7952
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3489 - loss: 1.7956
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3487 - loss: 1.7958
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3486 - loss: 1.7959
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7960
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3484 - loss: 1.7959
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3483 - loss: 1.7959
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7958
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3481 - loss: 1.7957
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3481 - loss: 1.7955
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3480 - loss: 1.7953
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3480 - loss: 1.7953
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7952
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7951
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7950
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7949
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7947
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7946
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7945
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7945
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3478 - loss: 1.7945
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3478 - loss: 1.7944
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7944
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7942
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7941
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7939
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7938
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7936
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7935
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7933
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7932
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7931 - val_accuracy: 0.3634 - val_loss: 1.7502
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.5689
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3920 - loss: 1.6794  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3745 - loss: 1.6983
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7084
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7194
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7238
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7260
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7279
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7296
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7320
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7343
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7359
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7367
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7370
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7373
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7374
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7374
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7375
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7377
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7379
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7382
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7387
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7391
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7395
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7397
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7400
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7402
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7405
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7408
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7410
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7413
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7416
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7419
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7421
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7425
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7428
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7431
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7435
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7438
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7440
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7443
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7446
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7449
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7452
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7455
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7456 - val_accuracy: 0.3713 - val_loss: 1.7580
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.6812
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3622 - loss: 1.6599  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7043
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7220
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7249
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7219
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7181
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7168
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3739 - loss: 1.7154
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3749 - loss: 1.7150
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3755 - loss: 1.7152
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7155
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7164
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7177
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7188
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7195
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3756 - loss: 1.7203
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3754 - loss: 1.7210
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7219
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3750 - loss: 1.7227
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3749 - loss: 1.7232
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3748 - loss: 1.7237
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3747 - loss: 1.7241
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3745 - loss: 1.7244
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7247
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3742 - loss: 1.7250
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7250
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3740 - loss: 1.7251
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3739 - loss: 1.7252
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3738 - loss: 1.7254
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3737 - loss: 1.7256
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7258
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7261
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3732 - loss: 1.7264
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3730 - loss: 1.7267
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7270
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7272
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3726 - loss: 1.7274
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7275
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7277
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7279
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3720 - loss: 1.7280
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7282
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7283
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7283
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7284 - val_accuracy: 0.3804 - val_loss: 1.7325
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.5240
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3669 - loss: 1.6772  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3675 - loss: 1.6896
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3656 - loss: 1.6998
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7053
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7077
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7084
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7095
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7113
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7126
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7141
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7151
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7158
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7158
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7155
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7154
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7153
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7151
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7151
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7152
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7155
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7158
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7162
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7167
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7172
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7177
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7183
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7188
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7191
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7194
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7196
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7198
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7200
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7201
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7202
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7202
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7202
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7203
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7203
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7203
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7203
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7203
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7203
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7203
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7203
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7203
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7203 - val_accuracy: 0.3697 - val_loss: 1.7662
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.5333
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4280 - loss: 1.5642  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4177 - loss: 1.6035
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4070 - loss: 1.6180
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4002 - loss: 1.6315
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3964 - loss: 1.6409
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3943 - loss: 1.6461
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3929 - loss: 1.6503
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3920 - loss: 1.6531
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3914 - loss: 1.6551
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6571
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3898 - loss: 1.6592
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3889 - loss: 1.6609
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3880 - loss: 1.6625
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3873 - loss: 1.6639
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6653
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3858 - loss: 1.6667
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3852 - loss: 1.6680
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6695
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3840 - loss: 1.6710
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6725
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3829 - loss: 1.6739
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6751
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3821 - loss: 1.6762
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6770
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3816 - loss: 1.6778
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3814 - loss: 1.6786
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3812 - loss: 1.6794
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3809 - loss: 1.6801
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3807 - loss: 1.6808
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3806 - loss: 1.6815
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3804 - loss: 1.6821
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3803 - loss: 1.6826
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3802 - loss: 1.6830
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3802 - loss: 1.6834
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3801 - loss: 1.6838
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3801 - loss: 1.6841
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3801 - loss: 1.6844
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3801 - loss: 1.6847
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3800 - loss: 1.6849
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3799 - loss: 1.6851
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3799 - loss: 1.6853
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3799 - loss: 1.6854
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3798 - loss: 1.6854
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3798 - loss: 1.6855
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3798 - loss: 1.6855
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3798 - loss: 1.6855 - val_accuracy: 0.3800 - val_loss: 1.7384
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.5056
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3736 - loss: 1.6922  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7222
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3692 - loss: 1.7302
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7309
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7310
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3680 - loss: 1.7295
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7261
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7243
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7231
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7214
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7200
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7185
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7176
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7169
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7160
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3730 - loss: 1.7146
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3732 - loss: 1.7134
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7122
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3738 - loss: 1.7110
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3740 - loss: 1.7100
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3742 - loss: 1.7090
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3744 - loss: 1.7083
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3747 - loss: 1.7071
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3750 - loss: 1.7060
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7050
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3754 - loss: 1.7041
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3756 - loss: 1.7032
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7024
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3761 - loss: 1.7015
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7008
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7001
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3767 - loss: 1.6994
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3769 - loss: 1.6988
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6981
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3773 - loss: 1.6974
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.6968
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3776 - loss: 1.6963
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3778 - loss: 1.6958
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3779 - loss: 1.6954
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3780 - loss: 1.6950
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3781 - loss: 1.6947
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.6943
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.6940
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.6938
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3784 - loss: 1.6935
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3784 - loss: 1.6934 - val_accuracy: 0.3804 - val_loss: 1.7598
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 1.7934
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4019 - loss: 1.6617  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4099 - loss: 1.6435
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4115 - loss: 1.6441
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4117 - loss: 1.6431
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4104 - loss: 1.6427
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4086 - loss: 1.6428
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4067 - loss: 1.6432
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4059 - loss: 1.6426
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4054 - loss: 1.6425
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4052 - loss: 1.6420
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4046 - loss: 1.6420
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4041 - loss: 1.6423
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4037 - loss: 1.6425
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6427
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4031 - loss: 1.6432
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4027 - loss: 1.6438
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4023 - loss: 1.6443
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4020 - loss: 1.6447
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4015 - loss: 1.6452
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4010 - loss: 1.6459
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4006 - loss: 1.6465
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4002 - loss: 1.6472
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3997 - loss: 1.6478
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3993 - loss: 1.6483
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3989 - loss: 1.6487
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3986 - loss: 1.6491
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3983 - loss: 1.6494
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3981 - loss: 1.6496
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3978 - loss: 1.6499
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3975 - loss: 1.6501
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3973 - loss: 1.6502
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6504
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6505
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6506
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3965 - loss: 1.6507
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6508
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3962 - loss: 1.6509
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6510
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3958 - loss: 1.6511
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3957 - loss: 1.6513
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6515
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6517
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3952 - loss: 1.6519
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3950 - loss: 1.6522
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3949 - loss: 1.6523 - val_accuracy: 0.3802 - val_loss: 1.7417
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.3750 - loss: 1.5417
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4119 - loss: 1.5411  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4169 - loss: 1.5606
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4159 - loss: 1.5778
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4133 - loss: 1.5922
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4107 - loss: 1.5996
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4081 - loss: 1.6048
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4061 - loss: 1.6083
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4043 - loss: 1.6112
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4026 - loss: 1.6139
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4013 - loss: 1.6166
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4003 - loss: 1.6183
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3997 - loss: 1.6193
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3993 - loss: 1.6203
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3987 - loss: 1.6215
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3983 - loss: 1.6224
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3978 - loss: 1.6233
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3975 - loss: 1.6242
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3972 - loss: 1.6249
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6254
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6259
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6263
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6268
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6272
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6277
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3965 - loss: 1.6281
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3965 - loss: 1.6285
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3964 - loss: 1.6287
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6291
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6295
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3962 - loss: 1.6299
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6303
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3959 - loss: 1.6307
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3958 - loss: 1.6311
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3958 - loss: 1.6314
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3957 - loss: 1.6317
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3956 - loss: 1.6320
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6322
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6324
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6326
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3954 - loss: 1.6329
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3954 - loss: 1.6331
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6334
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6337
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3952 - loss: 1.6338 - val_accuracy: 0.3865 - val_loss: 1.7650

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 1s/step
[1m45/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:25:19.390989: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:46[0m 1s/step
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m109/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 936us/step
[1m165/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 921us/step
[1m218/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 928us/step
[1m276/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 915us/step
[1m329/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 921us/step
[1m387/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 913us/step
[1m444/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 910us/step
[1m501/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 906us/step
[1m558/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 904us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 971us/step
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 927us/step
[1m166/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 919us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 36.82 [%]
Global F1 score (validation) = 36.73 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.2122842  0.19798866 0.22555196 ... 0.00216774 0.18911728 0.02282858]
 [0.22299002 0.20173335 0.15871155 ... 0.01096599 0.17615084 0.08049201]
 [0.23068091 0.20656003 0.20108612 ... 0.00458317 0.19927186 0.04781336]
 ...
 [0.21149614 0.22172962 0.20760214 ... 0.00382357 0.15335298 0.01829242]
 [0.19641367 0.21712008 0.19058292 ... 0.00419905 0.13591933 0.01174878]
 [0.2092361  0.1928965  0.22478075 ... 0.00106419 0.21428218 0.04475689]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 44.57 [%]
Global accuracy score (test) = 34.42 [%]
Global F1 score (train) = 44.02 [%]
Global F1 score (test) = 34.36 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.13      0.11      0.12       184
 CAMINAR CON MÓVIL O LIBRO       0.26      0.34      0.29       184
       CAMINAR USUAL SPEED       0.18      0.23      0.20       184
            CAMINAR ZIGZAG       0.63      0.48      0.55       184
          DE PIE BARRIENDO       0.32      0.38      0.34       184
   DE PIE DOBLANDO TOALLAS       0.45      0.14      0.21       184
    DE PIE MOVIENDO LIBROS       0.31      0.48      0.37       184
          DE PIE USANDO PC       0.45      0.31      0.37       184
        FASE REPOSO CON K5       0.87      0.70      0.77       184
INCREMENTAL CICLOERGOMETRO       0.68      0.57      0.62       184
           SENTADO LEYENDO       0.31      0.54      0.40       184
         SENTADO USANDO PC       0.13      0.10      0.12       184
      SENTADO VIENDO LA TV       0.20      0.22      0.21       184
   SUBIR Y BAJAR ESCALERAS       0.27      0.16      0.20       184
                    TROTAR       0.37      0.41      0.39       161

                  accuracy                           0.34      2737
                 macro avg       0.37      0.34      0.34      2737
              weighted avg       0.37      0.34      0.34      2737


Accuracy capturado en la ejecución 4: 34.42 [%]
F1-score capturado en la ejecución 4: 34.36 [%]

=== EJECUCIÓN 5 ===

--- TRAIN (ejecución 5) ---

--- TEST (ejecución 5) ---
2025-10-31 15:25:32.624400: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:25:32.635787: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761920732.648949 1656157 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761920732.653270 1656157 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761920732.663112 1656157 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920732.663133 1656157 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920732.663135 1656157 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920732.663136 1656157 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:25:32.666435: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761920735.027933 1656157 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761920738.129594 1656280 service.cc:152] XLA service 0x7d53500156b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761920738.129637 1656280 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:25:38.193475: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761920738.611553 1656280 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761920741.230045 1656280 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45:26[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.1032
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.0446 - loss: 3.4075        
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0516 - loss: 3.3992
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0559 - loss: 3.3889
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0591 - loss: 3.3787
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0616 - loss: 3.3658
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0633 - loss: 3.3516
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0647 - loss: 3.3382
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0660 - loss: 3.3248
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0674 - loss: 3.3095
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0688 - loss: 3.2963
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0699 - loss: 3.2848
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0710 - loss: 3.2726
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0723 - loss: 3.2600
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0737 - loss: 3.2480
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0749 - loss: 3.2374
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0761 - loss: 3.2265
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0771 - loss: 3.2170
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0782 - loss: 3.2069
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0791 - loss: 3.1977
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0800 - loss: 3.1888
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0808 - loss: 3.1800
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0815 - loss: 3.1717
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0822 - loss: 3.1640
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0828 - loss: 3.1567
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0835 - loss: 3.1491
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0841 - loss: 3.1414
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0847 - loss: 3.1349
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0855 - loss: 3.1271
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0862 - loss: 3.1198
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0868 - loss: 3.1130
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0875 - loss: 3.1061
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0881 - loss: 3.0995
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0888 - loss: 3.0928
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0894 - loss: 3.0866
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0900 - loss: 3.0808
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0906 - loss: 3.0745
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0912 - loss: 3.0688
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0918 - loss: 3.0627
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0924 - loss: 3.0570
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0930 - loss: 3.0510
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0935 - loss: 3.0461
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0940 - loss: 3.0408
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0945 - loss: 3.0358
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0950 - loss: 3.0307
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.0950 - loss: 3.0305
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.0950 - loss: 3.0303 - val_accuracy: 0.1817 - val_loss: 2.2979
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.2371
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1879 - loss: 2.4872  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1724 - loss: 2.4963
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1674 - loss: 2.4910
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1642 - loss: 2.4921
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1620 - loss: 2.4954
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1601 - loss: 2.5000
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1585 - loss: 2.5049
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1572 - loss: 2.5079
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1562 - loss: 2.5095
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1558 - loss: 2.5100
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1553 - loss: 2.5106
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1549 - loss: 2.5113
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1545 - loss: 2.5118
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1542 - loss: 2.5120
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1540 - loss: 2.5116
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1539 - loss: 2.5112
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1537 - loss: 2.5109
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1536 - loss: 2.5104
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1536 - loss: 2.5095
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.5086
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1536 - loss: 2.5076
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1536 - loss: 2.5068
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1536 - loss: 2.5061
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1536 - loss: 2.5053
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1536 - loss: 2.5045
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1536 - loss: 2.5038
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1537 - loss: 2.5029
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1537 - loss: 2.5021
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1537 - loss: 2.5013
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1538 - loss: 2.5005
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1538 - loss: 2.4998
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1538 - loss: 2.4990
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1539 - loss: 2.4983
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1539 - loss: 2.4976
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1539 - loss: 2.4968
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1540 - loss: 2.4960
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1540 - loss: 2.4953
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1540 - loss: 2.4945
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1541 - loss: 2.4937
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1542 - loss: 2.4929
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1542 - loss: 2.4922
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1543 - loss: 2.4914
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1544 - loss: 2.4906
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1544 - loss: 2.4898
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1544 - loss: 2.4897 - val_accuracy: 0.2096 - val_loss: 2.1773
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.1108
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2147 - loss: 2.3034  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2048 - loss: 2.3251
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1978 - loss: 2.3354
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1934 - loss: 2.3405
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1913 - loss: 2.3425
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1900 - loss: 2.3450
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1894 - loss: 2.3454
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1886 - loss: 2.3453
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1880 - loss: 2.3451
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1874 - loss: 2.3450
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1868 - loss: 2.3446
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1863 - loss: 2.3442
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.3437
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1853 - loss: 2.3432
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1850 - loss: 2.3430
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.3426
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1841 - loss: 2.3421
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.3415
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1832 - loss: 2.3411
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1828 - loss: 2.3409
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1823 - loss: 2.3405
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1820 - loss: 2.3402
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1816 - loss: 2.3400
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1813 - loss: 2.3398
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1810 - loss: 2.3396
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1808 - loss: 2.3393
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1805 - loss: 2.3390
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1803 - loss: 2.3387
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1801 - loss: 2.3383
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1800 - loss: 2.3380
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1799 - loss: 2.3376
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.3371
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.3366
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.3362
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.3357
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.3351
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.3346
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.3340
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.3335
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3330
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3325
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.3320
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.3314
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.3309
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1792 - loss: 2.3309 - val_accuracy: 0.2266 - val_loss: 2.0990
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.0625 - loss: 2.1890
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1443 - loss: 2.2718  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1502 - loss: 2.2834
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1549 - loss: 2.2794
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1577 - loss: 2.2789
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1597 - loss: 2.2813
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1610 - loss: 2.2820
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1626 - loss: 2.2798
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1647 - loss: 2.2756
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1667 - loss: 2.2722
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1680 - loss: 2.2705
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1690 - loss: 2.2688
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1700 - loss: 2.2675
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.2663
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1723 - loss: 2.2647
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1732 - loss: 2.2632
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1741 - loss: 2.2615
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1749 - loss: 2.2600
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1756 - loss: 2.2588
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1762 - loss: 2.2578
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1768 - loss: 2.2573
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.2568
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.2563
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.2559
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1789 - loss: 2.2556
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.2552
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.2548
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.2544
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1806 - loss: 2.2540
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1810 - loss: 2.2536
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1814 - loss: 2.2532
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1818 - loss: 2.2529
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1821 - loss: 2.2525
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1825 - loss: 2.2522
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.2519
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1831 - loss: 2.2515
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2512
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2508
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1840 - loss: 2.2504
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1842 - loss: 2.2501
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2498
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2495
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2493
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1851 - loss: 2.2490
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2488 - val_accuracy: 0.2481 - val_loss: 2.0536
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.4206
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1700 - loss: 2.2802  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1806 - loss: 2.2612
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1832 - loss: 2.2607
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1848 - loss: 2.2581
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2546
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1860 - loss: 2.2506
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1872 - loss: 2.2455
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1878 - loss: 2.2417
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1887 - loss: 2.2378
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1895 - loss: 2.2343
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1903 - loss: 2.2308
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1909 - loss: 2.2276
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1915 - loss: 2.2246
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1920 - loss: 2.2223
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1924 - loss: 2.2204
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1928 - loss: 2.2187
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1933 - loss: 2.2171
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1936 - loss: 2.2160
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1939 - loss: 2.2151
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1942 - loss: 2.2141
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1944 - loss: 2.2133
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1945 - loss: 2.2125
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1947 - loss: 2.2117
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1948 - loss: 2.2110
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1950 - loss: 2.2103
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1952 - loss: 2.2095
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1954 - loss: 2.2088
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1956 - loss: 2.2081
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1958 - loss: 2.2075
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1960 - loss: 2.2068
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1962 - loss: 2.2062
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1964 - loss: 2.2056
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1966 - loss: 2.2049
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1968 - loss: 2.2042
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1970 - loss: 2.2035
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1972 - loss: 2.2030
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1974 - loss: 2.2024
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1976 - loss: 2.2018
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1978 - loss: 2.2011
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1979 - loss: 2.2004
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1981 - loss: 2.1997
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.1991
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1985 - loss: 2.1986
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1987 - loss: 2.1980
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1987 - loss: 2.1979 - val_accuracy: 0.2379 - val_loss: 2.0177
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4247
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2042 - loss: 2.1353  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2166 - loss: 2.1292
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2205 - loss: 2.1244
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2218 - loss: 2.1200
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2225 - loss: 2.1179
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1172
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1172
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2240 - loss: 2.1174
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2243 - loss: 2.1176
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2248 - loss: 2.1182
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1187
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.1198
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2258 - loss: 2.1210
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2260 - loss: 2.1219
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2263 - loss: 2.1225
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2265 - loss: 2.1229
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2268 - loss: 2.1232
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2270 - loss: 2.1234
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2273 - loss: 2.1235
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2275 - loss: 2.1235
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2277 - loss: 2.1236
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2279 - loss: 2.1236
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2281 - loss: 2.1235
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2283 - loss: 2.1234
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2285 - loss: 2.1233
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2287 - loss: 2.1232
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2289 - loss: 2.1231
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2291 - loss: 2.1230
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2293 - loss: 2.1228
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2295 - loss: 2.1226
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2298 - loss: 2.1225
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2300 - loss: 2.1224
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2302 - loss: 2.1223
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2304 - loss: 2.1222
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2305 - loss: 2.1220
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2307 - loss: 2.1219
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2308 - loss: 2.1218
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2309 - loss: 2.1216
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2311 - loss: 2.1214
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2312 - loss: 2.1212
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2313 - loss: 2.1211
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2314 - loss: 2.1209
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2316 - loss: 2.1207
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.1206
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2317 - loss: 2.1205 - val_accuracy: 0.2840 - val_loss: 1.9696
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.1667
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2495 - loss: 2.0211  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2501 - loss: 2.0428
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2476 - loss: 2.0618
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2474 - loss: 2.0712
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2475 - loss: 2.0765
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.0777
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2485 - loss: 2.0783
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2483 - loss: 2.0792
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2484 - loss: 2.0793
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2487 - loss: 2.0784
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.0774
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2494 - loss: 2.0764
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.0754
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.0746
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2501 - loss: 2.0739
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.0737
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.0736
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0735
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0734
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.0732
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.0729
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.0726
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0724
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2518 - loss: 2.0722
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2521 - loss: 2.0719
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2525 - loss: 2.0716
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2527 - loss: 2.0713
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2529 - loss: 2.0708
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.0704
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2534 - loss: 2.0699
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2536 - loss: 2.0695
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0691
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2540 - loss: 2.0688
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.0684
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.0680
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.0676
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2549 - loss: 2.0672
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.0668
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.0663
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.0659
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2557 - loss: 2.0655
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2559 - loss: 2.0652
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.0649
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2561 - loss: 2.0648 - val_accuracy: 0.3301 - val_loss: 1.8695
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.0418
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2858 - loss: 2.0186  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2803 - loss: 2.0158
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2796 - loss: 2.0075
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2793 - loss: 2.0043
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2785 - loss: 2.0014
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2781 - loss: 1.9994
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2775 - loss: 1.9983
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2767 - loss: 1.9982
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2759 - loss: 1.9981
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2754 - loss: 1.9975
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2752 - loss: 1.9962
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2749 - loss: 1.9953
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2747 - loss: 1.9947
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2745 - loss: 1.9942
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2742 - loss: 1.9935
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2738 - loss: 1.9929
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 1.9927
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2732 - loss: 1.9925
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2730 - loss: 1.9923
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2729 - loss: 1.9921
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 1.9922
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 1.9924
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2727 - loss: 1.9925
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 1.9925
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 1.9927
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 1.9930
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2728 - loss: 1.9932
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 1.9934
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 1.9935
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 1.9936
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2731 - loss: 1.9937
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2732 - loss: 1.9937
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2733 - loss: 1.9938
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2734 - loss: 1.9938
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2735 - loss: 1.9938
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2736 - loss: 1.9938
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 1.9937
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2739 - loss: 1.9937
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 1.9936
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 1.9935
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2742 - loss: 1.9934
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2744 - loss: 1.9932
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2745 - loss: 1.9931
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2745 - loss: 1.9930 - val_accuracy: 0.3402 - val_loss: 1.8123
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 1.6692
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2672 - loss: 1.9697  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2788 - loss: 1.9511
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9497
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2843 - loss: 1.9527
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2860 - loss: 1.9530
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 1.9566
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2867 - loss: 1.9589
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2872 - loss: 1.9596
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 1.9593
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 1.9584
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2895 - loss: 1.9577
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2901 - loss: 1.9571
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2905 - loss: 1.9570
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2907 - loss: 1.9569
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9565
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2913 - loss: 1.9559
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9552
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2919 - loss: 1.9544
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2921 - loss: 1.9539
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9535
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 1.9532
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 1.9529
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9526
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9523
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9520
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9518
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9517
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9515
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9513
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 1.9511
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 1.9508
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 1.9506
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 1.9504
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9502
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9502
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 1.9501
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 1.9501
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 1.9501
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 1.9500
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 1.9500
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 1.9500
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 1.9500
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 1.9501
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 1.9501
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2919 - loss: 1.9501 - val_accuracy: 0.3280 - val_loss: 1.7826
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.4375 - loss: 1.6047
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3023 - loss: 1.8657  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8805
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3058 - loss: 1.8873
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3050 - loss: 1.8942
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 1.8985
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 1.9023
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 1.9057
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 1.9083
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 1.9101
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 1.9113
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 1.9119
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 1.9122
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9124
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9126
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9129
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 1.9130
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9132
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9133
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9133
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9134
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9136
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9138
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 1.9140
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 1.9141
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9143
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9143
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9143
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9142
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 1.9142
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 1.9142
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2992 - loss: 1.9142
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9141
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 1.9140
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2997 - loss: 1.9139
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 1.9138
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2999 - loss: 1.9138
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3000 - loss: 1.9138
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3001 - loss: 1.9138
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 1.9137
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 1.9136
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 1.9136
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9135
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9134
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9133 - val_accuracy: 0.3558 - val_loss: 1.7901
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0572
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3651 - loss: 1.8290  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8674
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3256 - loss: 1.8777
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3199 - loss: 1.8861
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3172 - loss: 1.8900
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 1.8902
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 1.8903
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 1.8904
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 1.8905
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 1.8899
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 1.8893
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 1.8893
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 1.8895
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 1.8899
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 1.8904
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3121 - loss: 1.8907
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3120 - loss: 1.8910
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 1.8910
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 1.8911
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 1.8912
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 1.8911
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8910
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 1.8910
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8910
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8912
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8912
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8913
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8914
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8916
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8918
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8919
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8921
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8922
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 1.8922
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8923
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8923
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 1.8924
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 1.8923
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 1.8923
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 1.8923
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 1.8923
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 1.8923
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 1.8923
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3123 - loss: 1.8923 - val_accuracy: 0.3619 - val_loss: 1.7548
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7520
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7474  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3369 - loss: 1.8005
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3277 - loss: 1.8132
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3224 - loss: 1.8232
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8307
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8358
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3187 - loss: 1.8367
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8370
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8365
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8360
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 1.8358
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8357
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 1.8355
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 1.8351
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8351
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3206 - loss: 1.8354
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 1.8360
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3209 - loss: 1.8368
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 1.8374
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 1.8381
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 1.8385
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3215 - loss: 1.8388
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 1.8391
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 1.8393
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 1.8396
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 1.8400
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 1.8402
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 1.8404
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 1.8405
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 1.8407
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.8409
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 1.8411
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3228 - loss: 1.8412
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 1.8414
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 1.8415
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 1.8416
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 1.8417
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 1.8419
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 1.8420
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 1.8422
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 1.8424
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 1.8425
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 1.8427
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8428
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8428 - val_accuracy: 0.3549 - val_loss: 1.7596
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1265
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8697  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3261 - loss: 1.8638
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8588
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8490
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3275 - loss: 1.8426
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 1.8385
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3293 - loss: 1.8363
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8348
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3304 - loss: 1.8337
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3309 - loss: 1.8329
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8325
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8318
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8315
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8313
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 1.8311
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8308
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 1.8305
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8300
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8296
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8292
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8288
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8284
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3349 - loss: 1.8282
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3351 - loss: 1.8280
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8278
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8275
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3355 - loss: 1.8273
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8270
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3358 - loss: 1.8268
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3358 - loss: 1.8266
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3358 - loss: 1.8265
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8264
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8263
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8262
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8261
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8261
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8260
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8258
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8257
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8255
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8254
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8252
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8250
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8250 - val_accuracy: 0.3647 - val_loss: 1.7452
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9790
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3311 - loss: 1.9629  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3363 - loss: 1.9205
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3367 - loss: 1.8936
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8792
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8704
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8610
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8549
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3386 - loss: 1.8500
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8465
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8434
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8422
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8408
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8396
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8385
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8374
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8366
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8356
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8347
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8339
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8330
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8322
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8314
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8307
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3404 - loss: 1.8300
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8293
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3406 - loss: 1.8286
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8278
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3408 - loss: 1.8271
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8265
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3411 - loss: 1.8260
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3412 - loss: 1.8253
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3412 - loss: 1.8248
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8244
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8239
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8235
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8230
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8225
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8219
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8215
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3420 - loss: 1.8211
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3421 - loss: 1.8207
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3422 - loss: 1.8202
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3423 - loss: 1.8197
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3424 - loss: 1.8194 - val_accuracy: 0.3630 - val_loss: 1.7472
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.5778
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3704 - loss: 1.7872  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3701 - loss: 1.7821
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7734
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7707
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3559 - loss: 1.7699
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7678
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7652
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7644
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7645
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3516 - loss: 1.7649
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3506 - loss: 1.7658
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3501 - loss: 1.7664
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7664
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7664
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7667
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7670
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7671
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7674
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.7678
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7679
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7682
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7684
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7687
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7689
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7693
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7697
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7701
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7705
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7707
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7709
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7710
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7711
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7712
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7711
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7711
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7712
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7713
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7715
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7716
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7718
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7720
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7721
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7723
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7725
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7725 - val_accuracy: 0.3604 - val_loss: 1.7377
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.4375 - loss: 1.4612
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3465 - loss: 1.7577  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3491 - loss: 1.7704
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3504 - loss: 1.7634
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3532 - loss: 1.7619
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7620
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7620
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7616
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7612
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7608
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7608
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7607
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7600
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7593
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7584
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7576
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7570
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7565
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7558
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7552
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7548
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7545
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7543
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7541
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7540
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7540
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7541
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7542
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7542
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7543
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7544
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7545
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7546
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7546
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7547
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7548
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7549
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7550
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7551
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7552
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7552
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7552
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7552
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7552 - val_accuracy: 0.3752 - val_loss: 1.7530
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.4375 - loss: 1.5919
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3889 - loss: 1.7429  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7516
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7493
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7446
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7457
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7488
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7516
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7539
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3673 - loss: 1.7549
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7548
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7541
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7530
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7521
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7516
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7509
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7501
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7493
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7487
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7482
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7477
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7472
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7467
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7463
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7461
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7458
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7454
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7449
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7446
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7441
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7437
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7432
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7429
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7425
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7422
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7419
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7416
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7414
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7412
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7409
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7407
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7405
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7403
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7401
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7399
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7398 - val_accuracy: 0.3732 - val_loss: 1.7530
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.3313
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3893 - loss: 1.6529  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6515
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6507
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6552
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3857 - loss: 1.6570
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3862 - loss: 1.6599
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3861 - loss: 1.6624
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6643
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3856 - loss: 1.6663
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3854 - loss: 1.6682
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3850 - loss: 1.6700
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3850 - loss: 1.6715
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3848 - loss: 1.6730
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6743
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6751
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6755
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6760
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3844 - loss: 1.6768
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3841 - loss: 1.6778
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3839 - loss: 1.6790
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3837 - loss: 1.6802
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3836 - loss: 1.6811
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6820
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6828
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6835
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3828 - loss: 1.6841
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6846
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3824 - loss: 1.6851
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6855
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3820 - loss: 1.6858
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6861
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6864
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3817 - loss: 1.6868
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3815 - loss: 1.6872
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3814 - loss: 1.6875
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3812 - loss: 1.6880
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3811 - loss: 1.6884
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3809 - loss: 1.6888
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3808 - loss: 1.6892
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3807 - loss: 1.6896
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3806 - loss: 1.6900
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3805 - loss: 1.6904
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3804 - loss: 1.6909
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3803 - loss: 1.6913
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3802 - loss: 1.6916 - val_accuracy: 0.3550 - val_loss: 1.7626
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.7500 - loss: 1.3941
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4458 - loss: 1.7266  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4076 - loss: 1.7285
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3939 - loss: 1.7199
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3888 - loss: 1.7135
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3862 - loss: 1.7100
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3840 - loss: 1.7063
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3826 - loss: 1.7033
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3818 - loss: 1.7014
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3813 - loss: 1.7001
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3809 - loss: 1.6989
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3803 - loss: 1.6978
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3797 - loss: 1.6969
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3793 - loss: 1.6965
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3788 - loss: 1.6961
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3783 - loss: 1.6963
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3779 - loss: 1.6966
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6969
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6971
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3767 - loss: 1.6972
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3764 - loss: 1.6973
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3762 - loss: 1.6974
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3759 - loss: 1.6975
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3757 - loss: 1.6975
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3757 - loss: 1.6976
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3756 - loss: 1.6977
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.6979
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.6981
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.6981
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.6981
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.6982
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.6981
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.6982
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.6982
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.6982
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.6981
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.6981
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3756 - loss: 1.6980
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3757 - loss: 1.6979
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3757 - loss: 1.6978
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3758 - loss: 1.6978
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3758 - loss: 1.6977
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3759 - loss: 1.6977
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3760 - loss: 1.6976
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3761 - loss: 1.6975
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3761 - loss: 1.6974 - val_accuracy: 0.3691 - val_loss: 1.7677
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.4465
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3905 - loss: 1.7228  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3823 - loss: 1.7377
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3814 - loss: 1.7381
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7392
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3788 - loss: 1.7353
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7336
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7318
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.7299
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3776 - loss: 1.7287
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3770 - loss: 1.7277
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7263
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7254
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3762 - loss: 1.7245
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3762 - loss: 1.7232
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7216
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3768 - loss: 1.7204
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7192
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7182
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3773 - loss: 1.7171
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3776 - loss: 1.7160
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3778 - loss: 1.7151
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.7139
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.7130
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3787 - loss: 1.7119
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3789 - loss: 1.7109
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7099
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3792 - loss: 1.7090
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3794 - loss: 1.7082
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.7074
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3797 - loss: 1.7066
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3799 - loss: 1.7058
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3801 - loss: 1.7050
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3802 - loss: 1.7042
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3804 - loss: 1.7035
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3805 - loss: 1.7030
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3806 - loss: 1.7024
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3807 - loss: 1.7018
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3808 - loss: 1.7013
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3810 - loss: 1.7007
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3811 - loss: 1.7001
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3812 - loss: 1.6996
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3814 - loss: 1.6991
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3815 - loss: 1.6985
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3816 - loss: 1.6980 - val_accuracy: 0.3682 - val_loss: 1.7854

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 1s/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:26:42.420956: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:11[0m 1s/step
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m106/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 960us/step
[1m156/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 973us/step
[1m213/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 950us/step
[1m269/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 939us/step
[1m320/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 947us/step
[1m376/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 941us/step
[1m431/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 937us/step
[1m490/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 927us/step
[1m545/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 926us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 945us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 51/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m105/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 965us/step
[1m154/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 985us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 38.65 [%]
Global F1 score (validation) = 34.53 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.21284686 0.21917899 0.19943646 ... 0.01118024 0.1526921  0.03272932]
 [0.22268668 0.25448543 0.18699078 ... 0.00265583 0.12887973 0.00985636]
 [0.23566665 0.23354958 0.20522107 ... 0.00391763 0.14877547 0.01556107]
 ...
 [0.21713544 0.1768915  0.18715774 ... 0.00038154 0.15286721 0.00849409]
 [0.22861402 0.19775051 0.17273115 ... 0.00038928 0.14014694 0.0052666 ]
 [0.23205666 0.24793175 0.20115426 ... 0.00332871 0.13874774 0.01598992]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.95 [%]
Global accuracy score (test) = 33.07 [%]
Global F1 score (train) = 42.9 [%]
Global F1 score (test) = 30.42 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.18      0.35      0.24       184
 CAMINAR CON MÓVIL O LIBRO       0.21      0.27      0.24       184
       CAMINAR USUAL SPEED       0.12      0.03      0.05       184
            CAMINAR ZIGZAG       0.45      0.62      0.52       184
          DE PIE BARRIENDO       0.30      0.40      0.34       184
   DE PIE DOBLANDO TOALLAS       0.35      0.09      0.15       184
    DE PIE MOVIENDO LIBROS       0.29      0.49      0.37       184
          DE PIE USANDO PC       0.33      0.60      0.43       184
        FASE REPOSO CON K5       0.81      0.60      0.69       184
INCREMENTAL CICLOERGOMETRO       0.73      0.51      0.60       184
           SENTADO LEYENDO       0.24      0.24      0.24       184
         SENTADO USANDO PC       0.23      0.32      0.27       184
      SENTADO VIENDO LA TV       0.00      0.00      0.00       184
   SUBIR Y BAJAR ESCALERAS       0.33      0.02      0.03       184
                    TROTAR       0.40      0.43      0.41       161

                  accuracy                           0.33      2737
                 macro avg       0.33      0.33      0.30      2737
              weighted avg       0.33      0.33      0.30      2737


Accuracy capturado en la ejecución 5: 33.07 [%]
F1-score capturado en la ejecución 5: 30.42 [%]

=== EJECUCIÓN 6 ===

--- TRAIN (ejecución 6) ---

--- TEST (ejecución 6) ---
2025-10-31 15:26:55.658096: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:26:55.669420: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761920815.682691 1659487 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761920815.686750 1659487 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761920815.696748 1659487 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920815.696779 1659487 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920815.696782 1659487 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920815.696784 1659487 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:26:55.700031: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761920818.087216 1659487 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761920821.233186 1659617 service.cc:152] XLA service 0x70c5cc01b5a0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761920821.233231 1659617 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:27:01.301317: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761920821.739770 1659617 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761920824.395630 1659617 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:55[0m 6s/step - accuracy: 0.0000e+00 - loss: 3.5464
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0410 - loss: 3.4969        
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0548 - loss: 3.4458
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0603 - loss: 3.4051
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0645 - loss: 3.3685
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0684 - loss: 3.3402
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0711 - loss: 3.3190
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0734 - loss: 3.2995
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0756 - loss: 3.2818
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0777 - loss: 3.2655
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0792 - loss: 3.2523
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0803 - loss: 3.2409
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0817 - loss: 3.2291
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0829 - loss: 3.2178
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0839 - loss: 3.2077
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0847 - loss: 3.1989
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0855 - loss: 3.1899
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0864 - loss: 3.1809
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0872 - loss: 3.1723
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0880 - loss: 3.1639
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0887 - loss: 3.1569
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0895 - loss: 3.1488
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0903 - loss: 3.1411
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0910 - loss: 3.1339
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0917 - loss: 3.1272
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0924 - loss: 3.1198
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0930 - loss: 3.1124
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0937 - loss: 3.1051
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0942 - loss: 3.0991
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0949 - loss: 3.0922
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0954 - loss: 3.0863
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0960 - loss: 3.0803
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0965 - loss: 3.0748
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0971 - loss: 3.0689
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0976 - loss: 3.0626
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0982 - loss: 3.0570
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0987 - loss: 3.0510
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0993 - loss: 3.0453
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0998 - loss: 3.0399
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1003 - loss: 3.0342
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1008 - loss: 3.0286
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1013 - loss: 3.0234
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1018 - loss: 3.0186
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1023 - loss: 3.0135
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1028 - loss: 3.0084
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1030 - loss: 3.0065
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1030 - loss: 3.0064 - val_accuracy: 0.1623 - val_loss: 2.3346
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.3649
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1558 - loss: 2.4949  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1491 - loss: 2.5017
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1449 - loss: 2.5096
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1428 - loss: 2.5155
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1426 - loss: 2.5185
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1431 - loss: 2.5204
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1434 - loss: 2.5226
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1435 - loss: 2.5242
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1436 - loss: 2.5253
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1439 - loss: 2.5256
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1441 - loss: 2.5260
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1444 - loss: 2.5261
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1448 - loss: 2.5260
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1453 - loss: 2.5253
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1458 - loss: 2.5243
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1462 - loss: 2.5232
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1465 - loss: 2.5222
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1467 - loss: 2.5213
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1469 - loss: 2.5202
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1471 - loss: 2.5192
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1472 - loss: 2.5184
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1474 - loss: 2.5175
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1475 - loss: 2.5167
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1476 - loss: 2.5157
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1477 - loss: 2.5148
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1478 - loss: 2.5140
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1479 - loss: 2.5133
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1480 - loss: 2.5126
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1480 - loss: 2.5120
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5113
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5107
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5101
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1482 - loss: 2.5096
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1482 - loss: 2.5089
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1482 - loss: 2.5082
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1483 - loss: 2.5077
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1483 - loss: 2.5070
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1484 - loss: 2.5063
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1485 - loss: 2.5055
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1485 - loss: 2.5048
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1486 - loss: 2.5039
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1486 - loss: 2.5031
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1486 - loss: 2.5022
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1487 - loss: 2.5015
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1487 - loss: 2.5010 - val_accuracy: 0.1780 - val_loss: 2.2348
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.0625 - loss: 2.6833
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1364 - loss: 2.4452  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1403 - loss: 2.4293
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1429 - loss: 2.4154
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1437 - loss: 2.4108
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1448 - loss: 2.4045
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1455 - loss: 2.4010
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1459 - loss: 2.3998
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1460 - loss: 2.3990
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1458 - loss: 2.3984
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1457 - loss: 2.3977
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1457 - loss: 2.3971
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1455 - loss: 2.3970
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1454 - loss: 2.3969
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1454 - loss: 2.3968
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1453 - loss: 2.3966
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1455 - loss: 2.3963
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1457 - loss: 2.3960
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1459 - loss: 2.3953
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1461 - loss: 2.3947
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1464 - loss: 2.3941
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1466 - loss: 2.3936
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1470 - loss: 2.3929
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1473 - loss: 2.3922
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1476 - loss: 2.3914
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1479 - loss: 2.3905
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1482 - loss: 2.3897
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1485 - loss: 2.3888
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1487 - loss: 2.3881
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1489 - loss: 2.3874
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1492 - loss: 2.3867
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1495 - loss: 2.3860
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1497 - loss: 2.3854
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1499 - loss: 2.3849
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1501 - loss: 2.3843
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1503 - loss: 2.3838
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1504 - loss: 2.3833
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1506 - loss: 2.3828
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1507 - loss: 2.3823
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1509 - loss: 2.3817
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1511 - loss: 2.3812
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1512 - loss: 2.3807
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1514 - loss: 2.3801
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1515 - loss: 2.3796
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1517 - loss: 2.3791
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1518 - loss: 2.3786
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1519 - loss: 2.3784 - val_accuracy: 0.1970 - val_loss: 2.1683
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.6197
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1060 - loss: 2.4573  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1311 - loss: 2.3931
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1404 - loss: 2.3717
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1454 - loss: 2.3611
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1492 - loss: 2.3510
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1520 - loss: 2.3423
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1542 - loss: 2.3362
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1562 - loss: 2.3312
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1571 - loss: 2.3283
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1579 - loss: 2.3258
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1589 - loss: 2.3234
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1598 - loss: 2.3212
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1605 - loss: 2.3195
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1613 - loss: 2.3180
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1620 - loss: 2.3167
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1626 - loss: 2.3155
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1631 - loss: 2.3145
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1636 - loss: 2.3137
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1639 - loss: 2.3129
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1643 - loss: 2.3120
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1646 - loss: 2.3113
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3105
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1653 - loss: 2.3097
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1657 - loss: 2.3090
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1660 - loss: 2.3083
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1663 - loss: 2.3075
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1667 - loss: 2.3068
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1670 - loss: 2.3061
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1673 - loss: 2.3054
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1676 - loss: 2.3047
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1679 - loss: 2.3041
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3035
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1683 - loss: 2.3030
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1685 - loss: 2.3024
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1687 - loss: 2.3019
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1689 - loss: 2.3013
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1690 - loss: 2.3008
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1691 - loss: 2.3004
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1693 - loss: 2.2999
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1694 - loss: 2.2995
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1695 - loss: 2.2992
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1696 - loss: 2.2987
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1697 - loss: 2.2983
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1698 - loss: 2.2979
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1699 - loss: 2.2975 - val_accuracy: 0.1830 - val_loss: 2.1229
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2247
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2011 - loss: 2.2452  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1859 - loss: 2.2551
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1814 - loss: 2.2541
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1798 - loss: 2.2523
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1792 - loss: 2.2491
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1787 - loss: 2.2455
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1789 - loss: 2.2433
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1793 - loss: 2.2415
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1793 - loss: 2.2406
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1793 - loss: 2.2399
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1791 - loss: 2.2396
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1789 - loss: 2.2395
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1786 - loss: 2.2392
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.2389
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1782 - loss: 2.2387
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.2386
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.2385
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.2384
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.2381
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.2379
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.2378
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.2378
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.2378
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.2378
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1781 - loss: 2.2378
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1782 - loss: 2.2377
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1783 - loss: 2.2376
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1785 - loss: 2.2374
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1786 - loss: 2.2372
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1788 - loss: 2.2371
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1790 - loss: 2.2369
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1791 - loss: 2.2368
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.2366
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.2365
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.2364
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.2362
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.2361
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1800 - loss: 2.2360
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1801 - loss: 2.2359
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.2358
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1803 - loss: 2.2357
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.2356
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1805 - loss: 2.2355
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1806 - loss: 2.2354
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1806 - loss: 2.2354 - val_accuracy: 0.2537 - val_loss: 2.0548
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3025
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2154 - loss: 2.1791  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2056 - loss: 2.1808
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2013 - loss: 2.1828
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1980 - loss: 2.1876
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1963 - loss: 2.1902
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1951 - loss: 2.1915
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1943 - loss: 2.1926
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1939 - loss: 2.1936
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1937 - loss: 2.1947
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1935 - loss: 2.1953
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1934 - loss: 2.1954
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1936 - loss: 2.1953
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1937 - loss: 2.1950
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1937 - loss: 2.1949
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1938 - loss: 2.1949
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1937 - loss: 2.1950
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1936 - loss: 2.1951
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1936 - loss: 2.1951
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1935 - loss: 2.1953
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1934 - loss: 2.1955
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1933 - loss: 2.1955
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1932 - loss: 2.1955
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1932 - loss: 2.1956
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1932 - loss: 2.1957
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1932 - loss: 2.1957
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1933 - loss: 2.1958
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1933 - loss: 2.1958
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1933 - loss: 2.1957
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1933 - loss: 2.1955
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1934 - loss: 2.1953
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1934 - loss: 2.1951
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1935 - loss: 2.1950
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1935 - loss: 2.1948
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1935 - loss: 2.1946
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1935 - loss: 2.1945
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1935 - loss: 2.1944
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1935 - loss: 2.1943
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1935 - loss: 2.1941
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1935 - loss: 2.1939
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1936 - loss: 2.1937
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1936 - loss: 2.1935
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1937 - loss: 2.1932
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1938 - loss: 2.1929
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1938 - loss: 2.1926
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1939 - loss: 2.1923
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1939 - loss: 2.1923 - val_accuracy: 0.2361 - val_loss: 2.0175
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.1092
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1695 - loss: 2.1695  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1789 - loss: 2.1581
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1839 - loss: 2.1520
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1896 - loss: 2.1464
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1938 - loss: 2.1451
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1965 - loss: 2.1454
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1987 - loss: 2.1464
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1999 - loss: 2.1475
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2008 - loss: 2.1475
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2015 - loss: 2.1476
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2024 - loss: 2.1475
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2032 - loss: 2.1471
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2039 - loss: 2.1464
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.1455
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2051 - loss: 2.1449
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2056 - loss: 2.1445
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2060 - loss: 2.1443
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2063 - loss: 2.1444
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2066 - loss: 2.1447
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2068 - loss: 2.1449
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2070 - loss: 2.1451
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2071 - loss: 2.1453
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2072 - loss: 2.1454
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2073 - loss: 2.1454
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2074 - loss: 2.1453
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2076 - loss: 2.1452
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2077 - loss: 2.1451
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2079 - loss: 2.1450
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2080 - loss: 2.1449
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.1449
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2083 - loss: 2.1448
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2085 - loss: 2.1446
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2087 - loss: 2.1445
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1444
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2090 - loss: 2.1443
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2091 - loss: 2.1443
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2093 - loss: 2.1442
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2095 - loss: 2.1442
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2097 - loss: 2.1440
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2099 - loss: 2.1439
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2101 - loss: 2.1438
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2103 - loss: 2.1437
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2105 - loss: 2.1435
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2107 - loss: 2.1434
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1433
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2110 - loss: 2.1432 - val_accuracy: 0.3153 - val_loss: 1.9601
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.0330
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2320 - loss: 2.0550  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2316 - loss: 2.0727
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2308 - loss: 2.0780
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2300 - loss: 2.0784
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2294 - loss: 2.0814
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2299 - loss: 2.0848
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2307 - loss: 2.0878
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2307 - loss: 2.0911
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2305 - loss: 2.0937
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2304 - loss: 2.0956
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2305 - loss: 2.0968
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2306 - loss: 2.0979
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2308 - loss: 2.0990
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2311 - loss: 2.1001
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2314 - loss: 2.1009
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2317 - loss: 2.1013
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2321 - loss: 2.1015
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.1015
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2328 - loss: 2.1015
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2330 - loss: 2.1015
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2332 - loss: 2.1014
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2334 - loss: 2.1013
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2335 - loss: 2.1012
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2337 - loss: 2.1011
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.1009
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.1007
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.1004
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2345 - loss: 2.1000
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2347 - loss: 2.0997
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2349 - loss: 2.0993
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2351 - loss: 2.0989
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2353 - loss: 2.0987
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2354 - loss: 2.0984
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2357 - loss: 2.0981
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2359 - loss: 2.0978
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2361 - loss: 2.0975
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2363 - loss: 2.0972
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2365 - loss: 2.0969
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2367 - loss: 2.0966
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2370 - loss: 2.0962
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2372 - loss: 2.0959
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2374 - loss: 2.0956
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2377 - loss: 2.0953
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2379 - loss: 2.0950
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2380 - loss: 2.0948 - val_accuracy: 0.3045 - val_loss: 1.9329
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.8525
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1154  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2285 - loss: 2.0836
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2320 - loss: 2.0763
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2330 - loss: 2.0689
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2341 - loss: 2.0618
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2354 - loss: 2.0577
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2366 - loss: 2.0546
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.0518
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2387 - loss: 2.0489
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2394 - loss: 2.0473
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2400 - loss: 2.0463
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2406 - loss: 2.0455
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2412 - loss: 2.0448
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2420 - loss: 2.0438
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2426 - loss: 2.0428
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.0416
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2437 - loss: 2.0406
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2442 - loss: 2.0399
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2446 - loss: 2.0394
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.0389
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2456 - loss: 2.0384
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2461 - loss: 2.0378
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2466 - loss: 2.0372
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2471 - loss: 2.0367
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2475 - loss: 2.0363
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2479 - loss: 2.0360
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2483 - loss: 2.0356
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.0352
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.0348
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2496 - loss: 2.0343
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2500 - loss: 2.0338
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0334
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.0330
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2513 - loss: 2.0326
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2517 - loss: 2.0322
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2520 - loss: 2.0318
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2524 - loss: 2.0315
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2527 - loss: 2.0311
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2531 - loss: 2.0308
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2535 - loss: 2.0305
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2539 - loss: 2.0302
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.0298
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.0295
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2549 - loss: 2.0293 - val_accuracy: 0.2799 - val_loss: 1.9271
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 1.9964
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2637 - loss: 2.0041  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2660 - loss: 1.9858
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2667 - loss: 1.9787
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2662 - loss: 1.9780
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2652 - loss: 1.9771
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2650 - loss: 1.9767
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2645 - loss: 1.9784
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 1.9809
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 1.9823
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2639 - loss: 1.9833
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2642 - loss: 1.9839
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2645 - loss: 1.9848
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2650 - loss: 1.9856
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 1.9862
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2659 - loss: 1.9869
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2662 - loss: 1.9877
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2665 - loss: 1.9884
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2668 - loss: 1.9889
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 1.9895
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 1.9900
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 1.9905
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2678 - loss: 1.9907
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2680 - loss: 1.9908
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2683 - loss: 1.9910
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2686 - loss: 1.9911
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2689 - loss: 1.9910
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2693 - loss: 1.9910
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2696 - loss: 1.9909
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 1.9909
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 1.9909
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 1.9909
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 1.9910
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2712 - loss: 1.9911
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 1.9912
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 1.9912
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 1.9913
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 1.9913
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2724 - loss: 1.9913
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 1.9913
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 1.9914
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 1.9914
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2731 - loss: 1.9914
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2733 - loss: 1.9915
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2735 - loss: 1.9915
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2735 - loss: 1.9915 - val_accuracy: 0.3010 - val_loss: 1.8940
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.6901
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2935 - loss: 1.9583  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9450
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2978 - loss: 1.9438
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9409
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9391
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 1.9374
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9370
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 1.9385
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2991 - loss: 1.9397
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 1.9404
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 1.9407
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 1.9412
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 1.9418
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 1.9419
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 1.9418
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9414
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2991 - loss: 1.9409
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9406
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9405
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9403
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9400
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2979 - loss: 1.9400
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9398
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2976 - loss: 1.9396
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2975 - loss: 1.9394
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9392
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2972 - loss: 1.9391
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2971 - loss: 1.9391
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 1.9391
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 1.9391
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 1.9392
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9392
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9392
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9391
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9391
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9391
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9391
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9391
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9390
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9389
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9389
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9389
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9389
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9389
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9389 - val_accuracy: 0.3095 - val_loss: 1.8683
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3273
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2691 - loss: 2.0152  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2783 - loss: 1.9961
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2810 - loss: 1.9813
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2826 - loss: 1.9703
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 1.9601
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 1.9517
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 1.9458
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 1.9421
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 1.9393
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2891 - loss: 1.9373
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2900 - loss: 1.9351
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2906 - loss: 1.9338
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2911 - loss: 1.9327
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9317
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9308
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2929 - loss: 1.9301
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 1.9294
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9291
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 1.9288
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 1.9286
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 1.9282
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2949 - loss: 1.9276
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9270
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2957 - loss: 1.9264
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2961 - loss: 1.9259
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9254
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9249
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2971 - loss: 1.9245
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2974 - loss: 1.9240
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9236
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9231
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9226
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9221
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 1.9217
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9212
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 1.9209
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 1.9205
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3001 - loss: 1.9200
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 1.9196
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9191
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 1.9187
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3012 - loss: 1.9183
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 1.9179
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9175
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3018 - loss: 1.9174 - val_accuracy: 0.3267 - val_loss: 1.8089
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9613
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7968  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3277 - loss: 1.8180
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8296
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3143 - loss: 1.8446
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3121 - loss: 1.8552
[1m 146/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3113 - loss: 1.8603
[1m 172/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3104 - loss: 1.8646
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3095 - loss: 1.8675
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 1.8707
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 1.8735
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 1.8752
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 1.8758
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 1.8763
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 1.8766
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 1.8768
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 1.8769
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 1.8768
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 1.8766
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 1.8761
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 1.8756
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 1.8751
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3054 - loss: 1.8746
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 1.8741
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 1.8736
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 1.8731
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 1.8727
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.8722
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8716
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 1.8709
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 1.8704
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 1.8699
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3073 - loss: 1.8694
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3074 - loss: 1.8690
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3077 - loss: 1.8686
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3079 - loss: 1.8682
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3081 - loss: 1.8680
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3082 - loss: 1.8678
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3084 - loss: 1.8676
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 1.8674
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 1.8672
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 1.8670
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.8668
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 1.8667
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 1.8666
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3099 - loss: 1.8665 - val_accuracy: 0.3739 - val_loss: 1.7692
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3750 - loss: 1.5890
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3156 - loss: 1.8203  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8621
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3107 - loss: 1.8669
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8667
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8664
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3110 - loss: 1.8665
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3113 - loss: 1.8668
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8671
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8675
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 1.8674
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8668
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8665
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8662
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8659
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 1.8656
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 1.8652
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 1.8651
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.8650
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.8649
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 1.8648
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 1.8649
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 1.8650
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 1.8649
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 1.8649
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 1.8648
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 1.8647
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3155 - loss: 1.8647
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3157 - loss: 1.8646
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3160 - loss: 1.8644
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3162 - loss: 1.8642
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8640
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3167 - loss: 1.8637
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8635
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 1.8633
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8631
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 1.8628
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8626
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8623
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8619
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3184 - loss: 1.8616
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3186 - loss: 1.8613
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8609
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8606
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3192 - loss: 1.8602
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8598
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3195 - loss: 1.8596 - val_accuracy: 0.3452 - val_loss: 1.7941
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.6732
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3458 - loss: 1.8643  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3540 - loss: 1.8311
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3594 - loss: 1.8086
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7995
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7911
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7865
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7825
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7806
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7793
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3508 - loss: 1.7789
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7794
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7795
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7796
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3489 - loss: 1.7800
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3484 - loss: 1.7806
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3480 - loss: 1.7811
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3475 - loss: 1.7815
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3469 - loss: 1.7822
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3462 - loss: 1.7829
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3457 - loss: 1.7835
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3453 - loss: 1.7840
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3449 - loss: 1.7846
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3446 - loss: 1.7851
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3443 - loss: 1.7854
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3441 - loss: 1.7855
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3438 - loss: 1.7856
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3436 - loss: 1.7857
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3435 - loss: 1.7858
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.7859
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3431 - loss: 1.7861
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3430 - loss: 1.7864
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.7866
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.7868
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.7870
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3424 - loss: 1.7873
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3422 - loss: 1.7876
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3421 - loss: 1.7879
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.7882
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.7885
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.7888
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3414 - loss: 1.7891
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3413 - loss: 1.7894
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7898
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 1.7900
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3410 - loss: 1.7901 - val_accuracy: 0.3639 - val_loss: 1.7616
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.6203
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3169 - loss: 1.7556  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3173 - loss: 1.7633
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3179 - loss: 1.7697
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3215 - loss: 1.7722
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3258 - loss: 1.7721
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 1.7700
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 1.7672
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3356 - loss: 1.7662
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3368 - loss: 1.7661
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3380 - loss: 1.7660
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3390 - loss: 1.7660
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3394 - loss: 1.7662
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.7665
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.7668
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 1.7669
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.7670
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3405 - loss: 1.7672
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.7675
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3408 - loss: 1.7681
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3410 - loss: 1.7686
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7693
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7700
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7705
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3412 - loss: 1.7708
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3412 - loss: 1.7711
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3414 - loss: 1.7713
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3415 - loss: 1.7715
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.7716
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.7718
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.7719
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3420 - loss: 1.7720
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3421 - loss: 1.7720
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3423 - loss: 1.7721
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3424 - loss: 1.7721
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.7721
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.7721
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.7721
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.7721
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3431 - loss: 1.7721
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3432 - loss: 1.7721
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.7721
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3434 - loss: 1.7721
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3435 - loss: 1.7721
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3436 - loss: 1.7720
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3437 - loss: 1.7720
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3437 - loss: 1.7720 - val_accuracy: 0.3747 - val_loss: 1.7478
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.5000 - loss: 1.3123
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7384  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3475 - loss: 1.7476
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7461
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7425
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7403
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7387
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7370
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7364
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7367
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7373
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7373
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7369
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7368
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7369
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7370
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7371
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7371
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7370
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7368
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7366
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7367
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7367
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7367
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7369
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7373
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7376
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7379
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7383
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7385
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7388
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7391
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7394
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7397
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7400
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7403
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7406
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7410
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7413
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7415
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7418
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7421
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7424
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7428
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7431
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7432 - val_accuracy: 0.3632 - val_loss: 1.7845
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 2.0604
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3945 - loss: 1.8140  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7924
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3760 - loss: 1.7753
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3756 - loss: 1.7661
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3748 - loss: 1.7609
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3744 - loss: 1.7579
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3745 - loss: 1.7550
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3745 - loss: 1.7529
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3740 - loss: 1.7527
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7526
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7528
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7531
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7534
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7535
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7537
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7540
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7542
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7545
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7548
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3672 - loss: 1.7549
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7550
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7550
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7549
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7549
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7547
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7545
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7543
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7540
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7538
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7535
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7532
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7529
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7525
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7522
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7519
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7516
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7513
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7509
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7505
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7502
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7499
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7497
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7494
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7492
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7490
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7489 - val_accuracy: 0.3856 - val_loss: 1.7399
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.4375 - loss: 1.3751
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7599  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7295
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7144
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7130
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7152
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7156
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7165
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7175
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7182
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7182
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7180
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7175
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7173
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7173
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7173
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7172
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7169
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7164
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7160
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7155
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7151
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7147
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7142
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7139
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7135
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7132
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7131
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7129
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7129
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7129
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7129
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7128
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7128
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7128
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7129
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7130
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7131
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7133
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7134
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7135
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7136
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7137
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7138
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7138
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7139 - val_accuracy: 0.3796 - val_loss: 1.7756
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 1.9463
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3297 - loss: 1.7720  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3396 - loss: 1.7570
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3473 - loss: 1.7481
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3516 - loss: 1.7412
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7405
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7415
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7411
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7402
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7394
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7384
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7367
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7354
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7340
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7324
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7304
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7286
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3617 - loss: 1.7272
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7258
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7244
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7232
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7220
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7207
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7196
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7184
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7174
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7165
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7157
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7152
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7147
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7142
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7138
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7134
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7130
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7125
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7122
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7119
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7115
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7112
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7110
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7108
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7106
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7105
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7104
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7103
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7103 - val_accuracy: 0.3658 - val_loss: 1.7899
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.5380
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4197 - loss: 1.5059  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4103 - loss: 1.5440
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4042 - loss: 1.5723
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4020 - loss: 1.5911
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4015 - loss: 1.6044
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4012 - loss: 1.6132
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4004 - loss: 1.6192
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3989 - loss: 1.6249
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3973 - loss: 1.6299
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3962 - loss: 1.6336
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3954 - loss: 1.6367
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3944 - loss: 1.6400
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6427
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6453
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3920 - loss: 1.6479
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3911 - loss: 1.6503
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3903 - loss: 1.6526
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3895 - loss: 1.6548
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3889 - loss: 1.6566
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3884 - loss: 1.6584
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6599
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3874 - loss: 1.6615
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6629
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6640
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3864 - loss: 1.6652
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3862 - loss: 1.6663
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6674
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3858 - loss: 1.6682
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3857 - loss: 1.6689
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3855 - loss: 1.6696
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.6702
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3853 - loss: 1.6708
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3851 - loss: 1.6713
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3850 - loss: 1.6718
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6722
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3848 - loss: 1.6726
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3848 - loss: 1.6729
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6732
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6735
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6739
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6742
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3844 - loss: 1.6745
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6748
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6749 - val_accuracy: 0.3798 - val_loss: 1.7502

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 1s/step
[1m49/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:28:08.985947: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:35[0m 1s/step
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m111/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 917us/step
[1m165/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 921us/step
[1m225/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 899us/step
[1m283/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 893us/step
[1m341/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 890us/step
[1m399/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 887us/step
[1m449/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 900us/step
[1m495/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 919us/step
[1m545/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 928us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 983us/step
[1m105/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 963us/step
[1m158/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 960us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 36.82 [%]
Global F1 score (validation) = 32.44 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.22659436 0.21209046 0.1794188  ... 0.00751196 0.13498525 0.02269921]
 [0.23676015 0.19022872 0.21203607 ... 0.00240354 0.18347816 0.01535958]
 [0.20729508 0.20166752 0.17399515 ... 0.01603165 0.12815979 0.0328826 ]
 ...
 [0.23991622 0.2074937  0.18546742 ... 0.00594045 0.14418899 0.01104136]
 [0.20735037 0.14918642 0.19981848 ... 0.00036727 0.1987539  0.0115708 ]
 [0.20642127 0.20154591 0.16083921 ... 0.00476648 0.09726227 0.00418733]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 44.55 [%]
Global accuracy score (test) = 31.42 [%]
Global F1 score (train) = 40.14 [%]
Global F1 score (test) = 28.49 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.19      0.64      0.29       184
 CAMINAR CON MÓVIL O LIBRO       0.18      0.06      0.09       184
       CAMINAR USUAL SPEED       0.07      0.01      0.02       184
            CAMINAR ZIGZAG       0.44      0.41      0.42       184
          DE PIE BARRIENDO       0.31      0.38      0.34       184
   DE PIE DOBLANDO TOALLAS       0.33      0.05      0.09       184
    DE PIE MOVIENDO LIBROS       0.29      0.48      0.36       184
          DE PIE USANDO PC       0.35      0.59      0.43       184
        FASE REPOSO CON K5       1.00      0.42      0.59       184
INCREMENTAL CICLOERGOMETRO       0.77      0.53      0.63       184
           SENTADO LEYENDO       0.00      0.00      0.00       184
         SENTADO USANDO PC       0.23      0.39      0.29       184
      SENTADO VIENDO LA TV       0.23      0.33      0.27       184
   SUBIR Y BAJAR ESCALERAS       0.13      0.02      0.04       184
                    TROTAR       0.40      0.42      0.41       161

                  accuracy                           0.31      2737
                 macro avg       0.33      0.32      0.28      2737
              weighted avg       0.33      0.31      0.28      2737


Accuracy capturado en la ejecución 6: 31.42 [%]
F1-score capturado en la ejecución 6: 28.49 [%]

=== EJECUCIÓN 7 ===

--- TRAIN (ejecución 7) ---

--- TEST (ejecución 7) ---
2025-10-31 15:28:22.134643: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:28:22.145860: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761920902.159140 1662975 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761920902.163184 1662975 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761920902.173215 1662975 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920902.173237 1662975 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920902.173239 1662975 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920902.173241 1662975 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:28:22.176325: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761920904.564538 1662975 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761920907.684787 1663090 service.cc:152] XLA service 0x792ba800c000 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761920907.684854 1663090 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:28:27.754351: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761920908.192827 1663090 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761920910.827872 1663090 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:08[0m 6s/step - accuracy: 0.0625 - loss: 3.2300
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0505 - loss: 3.3514    
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0580 - loss: 3.3466
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0621 - loss: 3.3333
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0638 - loss: 3.3240
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0657 - loss: 3.3119
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0678 - loss: 3.2949
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0697 - loss: 3.2784
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0713 - loss: 3.2639
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0729 - loss: 3.2496
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0742 - loss: 3.2362
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0754 - loss: 3.2239
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0766 - loss: 3.2130
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0778 - loss: 3.2014
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0790 - loss: 3.1909
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0802 - loss: 3.1807
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0812 - loss: 3.1708
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0822 - loss: 3.1611
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0830 - loss: 3.1521
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0838 - loss: 3.1430
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0846 - loss: 3.1332
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0854 - loss: 3.1240
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0862 - loss: 3.1155
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0870 - loss: 3.1070
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0878 - loss: 3.0990
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0885 - loss: 3.0916
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0892 - loss: 3.0849
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0898 - loss: 3.0783
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0905 - loss: 3.0720
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0911 - loss: 3.0654
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0917 - loss: 3.0590
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0922 - loss: 3.0537
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0927 - loss: 3.0480
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0932 - loss: 3.0429
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0937 - loss: 3.0372
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0943 - loss: 3.0313
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0948 - loss: 3.0261
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0953 - loss: 3.0207
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0959 - loss: 3.0152
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0964 - loss: 3.0099
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0969 - loss: 3.0045
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0973 - loss: 2.9997
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0978 - loss: 2.9951
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0982 - loss: 2.9903
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.0985 - loss: 2.9876
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.0985 - loss: 2.9874 - val_accuracy: 0.1654 - val_loss: 2.3463
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.5566
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1679 - loss: 2.4728  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1624 - loss: 2.4948
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1605 - loss: 2.5058
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1584 - loss: 2.5112
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1572 - loss: 2.5143
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1563 - loss: 2.5156
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1554 - loss: 2.5163
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1546 - loss: 2.5166
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1542 - loss: 2.5163
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1537 - loss: 2.5165
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1532 - loss: 2.5171
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1526 - loss: 2.5177
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1520 - loss: 2.5180
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1516 - loss: 2.5180
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1512 - loss: 2.5179
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1511 - loss: 2.5173
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1510 - loss: 2.5167
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1510 - loss: 2.5159
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1512 - loss: 2.5150
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1513 - loss: 2.5140
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1514 - loss: 2.5130
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1515 - loss: 2.5120
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1517 - loss: 2.5111
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1518 - loss: 2.5102
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1519 - loss: 2.5092
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1520 - loss: 2.5081
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1521 - loss: 2.5071
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1522 - loss: 2.5061
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1522 - loss: 2.5051
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1522 - loss: 2.5042
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1523 - loss: 2.5032
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1523 - loss: 2.5021
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1524 - loss: 2.5012
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1524 - loss: 2.5002
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1525 - loss: 2.4992
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1525 - loss: 2.4983
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1525 - loss: 2.4973
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1526 - loss: 2.4963
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1526 - loss: 2.4955
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1526 - loss: 2.4946
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1527 - loss: 2.4938
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1527 - loss: 2.4929
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1527 - loss: 2.4921
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1527 - loss: 2.4913
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1527 - loss: 2.4905 - val_accuracy: 0.1621 - val_loss: 2.2276
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.2282
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1396 - loss: 2.3376  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1475 - loss: 2.3466
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1526 - loss: 2.3510
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1549 - loss: 2.3529
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1573 - loss: 2.3534
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1588 - loss: 2.3540
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1601 - loss: 2.3559
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1613 - loss: 2.3568
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1624 - loss: 2.3573
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1632 - loss: 2.3579
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1639 - loss: 2.3581
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1645 - loss: 2.3580
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1651 - loss: 2.3578
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1656 - loss: 2.3573
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1660 - loss: 2.3569
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1663 - loss: 2.3564
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1665 - loss: 2.3559
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3554
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1670 - loss: 2.3548
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1671 - loss: 2.3542
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1672 - loss: 2.3536
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1674 - loss: 2.3528
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1675 - loss: 2.3521
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1677 - loss: 2.3514
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1678 - loss: 2.3509
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1679 - loss: 2.3505
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3499
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1682 - loss: 2.3495
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1683 - loss: 2.3490
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3485
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1685 - loss: 2.3480
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1686 - loss: 2.3476
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1687 - loss: 2.3471
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1688 - loss: 2.3468
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1689 - loss: 2.3465
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1690 - loss: 2.3462
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1691 - loss: 2.3458
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3455
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3451
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1693 - loss: 2.3448
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1694 - loss: 2.3444
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1695 - loss: 2.3440
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1695 - loss: 2.3436
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1696 - loss: 2.3433
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1696 - loss: 2.3430 - val_accuracy: 0.1896 - val_loss: 2.1782
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.8703
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1704 - loss: 2.3001  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1799 - loss: 2.2775
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1800 - loss: 2.2782
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1798 - loss: 2.2764
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1801 - loss: 2.2746
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1804 - loss: 2.2733
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1804 - loss: 2.2728
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1801 - loss: 2.2721
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1800 - loss: 2.2715
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1799 - loss: 2.2714
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1800 - loss: 2.2713
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1801 - loss: 2.2710
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1803 - loss: 2.2706
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1804 - loss: 2.2704
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1805 - loss: 2.2702
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1807 - loss: 2.2702
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1809 - loss: 2.2701
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1812 - loss: 2.2699
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1815 - loss: 2.2696
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1816 - loss: 2.2695
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.2695
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.2695
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.2695
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.2695
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1818 - loss: 2.2694
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1819 - loss: 2.2692
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1820 - loss: 2.2691
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1821 - loss: 2.2689
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1822 - loss: 2.2688
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1823 - loss: 2.2685
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2683
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1825 - loss: 2.2682
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1826 - loss: 2.2679
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1827 - loss: 2.2677
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.2674
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1829 - loss: 2.2672
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1831 - loss: 2.2669
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1831 - loss: 2.2667
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.2665
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1833 - loss: 2.2662
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2660
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2657
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2655
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2652
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2650 - val_accuracy: 0.1896 - val_loss: 2.1365
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.0738
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1631 - loss: 2.3022  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1769 - loss: 2.2680
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1811 - loss: 2.2551
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1827 - loss: 2.2452
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2411
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2371
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2345
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2332
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2325
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2314
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2304
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2297
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2292
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1832 - loss: 2.2287
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1830 - loss: 2.2283
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.2280
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.2277
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.2274
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.2272
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.2271
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1830 - loss: 2.2270
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1831 - loss: 2.2268
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1833 - loss: 2.2266
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2263
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2260
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2258
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1840 - loss: 2.2255
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1842 - loss: 2.2252
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1843 - loss: 2.2249
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1843 - loss: 2.2246
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1844 - loss: 2.2243
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2239
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2235
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.2230
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2226
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2222
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2218
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1851 - loss: 2.2215
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2212
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2209
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2206
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2203
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2200
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2198
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2197 - val_accuracy: 0.2000 - val_loss: 2.0598
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7752
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2462 - loss: 2.0188  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2336 - loss: 2.0731
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2256 - loss: 2.0999
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2221 - loss: 2.1150
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2207 - loss: 2.1210
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2197 - loss: 2.1236
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2188 - loss: 2.1254
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.1273
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2174 - loss: 2.1285
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2170 - loss: 2.1298
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2164 - loss: 2.1315
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2157 - loss: 2.1329
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2151 - loss: 2.1344
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2146 - loss: 2.1357
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2143 - loss: 2.1367
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2139 - loss: 2.1376
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2136 - loss: 2.1385
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2133 - loss: 2.1392
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2130 - loss: 2.1400
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2127 - loss: 2.1407
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.1415
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2122 - loss: 2.1421
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2119 - loss: 2.1428
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2118 - loss: 2.1433
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2116 - loss: 2.1438
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2115 - loss: 2.1442
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2114 - loss: 2.1446
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2113 - loss: 2.1451
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1455
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1458
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2111 - loss: 2.1461
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.1464
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1468
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2108 - loss: 2.1471
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2107 - loss: 2.1474
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2106 - loss: 2.1478
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2105 - loss: 2.1481
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2104 - loss: 2.1484
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2103 - loss: 2.1487
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2103 - loss: 2.1489
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2102 - loss: 2.1491
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2102 - loss: 2.1492
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2101 - loss: 2.1494
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2101 - loss: 2.1496
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2100 - loss: 2.1497
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2100 - loss: 2.1498 - val_accuracy: 0.2329 - val_loss: 2.0484
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8676
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2307 - loss: 2.0504  
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2247 - loss: 2.0675
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2225 - loss: 2.0808
[1m 114/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2230 - loss: 2.0895
[1m 140/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2225 - loss: 2.0953
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2221 - loss: 2.1003
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2211 - loss: 2.1046
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2205 - loss: 2.1079
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2205 - loss: 2.1092
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2207 - loss: 2.1099
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2207 - loss: 2.1105
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2209 - loss: 2.1111
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2211 - loss: 2.1119
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.1127
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2213 - loss: 2.1135
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2215 - loss: 2.1142
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2215 - loss: 2.1149
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2218 - loss: 2.1154
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2220 - loss: 2.1159
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2223 - loss: 2.1162
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2225 - loss: 2.1164
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2227 - loss: 2.1165
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2229 - loss: 2.1167
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2231 - loss: 2.1168
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2232 - loss: 2.1170
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2233 - loss: 2.1171
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1172
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1174
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2237 - loss: 2.1176
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2238 - loss: 2.1178
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2239 - loss: 2.1179
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2240 - loss: 2.1181
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1182
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2242 - loss: 2.1184
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2243 - loss: 2.1185
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.1185
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2247 - loss: 2.1185
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2248 - loss: 2.1185
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2250 - loss: 2.1185
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1185
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.1184
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.1184
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2257 - loss: 2.1183
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2257 - loss: 2.1183 - val_accuracy: 0.2405 - val_loss: 1.9967
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.4013
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2062 - loss: 2.1987  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2166 - loss: 2.1606
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2221 - loss: 2.1383
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2248 - loss: 2.1290
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2259 - loss: 2.1208
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2273 - loss: 2.1148
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2283 - loss: 2.1103
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2290 - loss: 2.1074
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.1049
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2302 - loss: 2.1033
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2307 - loss: 2.1021
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2313 - loss: 2.1009
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2317 - loss: 2.1004
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2321 - loss: 2.1000
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.0998
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2328 - loss: 2.0995
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2331 - loss: 2.0992
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2334 - loss: 2.0991
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2337 - loss: 2.0990
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2340 - loss: 2.0988
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2341 - loss: 2.0987
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2343 - loss: 2.0985
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2345 - loss: 2.0982
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2346 - loss: 2.0978
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2348 - loss: 2.0975
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2350 - loss: 2.0969
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2352 - loss: 2.0965
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2355 - loss: 2.0958
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2358 - loss: 2.0952
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2360 - loss: 2.0947
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2361 - loss: 2.0942
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2362 - loss: 2.0938
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2363 - loss: 2.0935
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2364 - loss: 2.0932
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2366 - loss: 2.0928
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2367 - loss: 2.0923
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2369 - loss: 2.0919
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2370 - loss: 2.0915
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2372 - loss: 2.0910
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2373 - loss: 2.0906
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2375 - loss: 2.0902
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2376 - loss: 2.0898
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2378 - loss: 2.0893
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2379 - loss: 2.0889
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2379 - loss: 2.0889 - val_accuracy: 0.2810 - val_loss: 1.9493
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 1.9294
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.2605 - loss: 2.0704  
[1m  43/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2675 - loss: 2.0669
[1m  68/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2651 - loss: 2.0609
[1m  94/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0539
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2622 - loss: 2.0534
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2614 - loss: 2.0543
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2613 - loss: 2.0547
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.0554
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0553
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2624 - loss: 2.0548
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2628 - loss: 2.0543
[1m 302/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0538
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0532
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2648 - loss: 2.0525
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2653 - loss: 2.0516
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2657 - loss: 2.0511
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0508
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0504
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0500
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0495
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0488
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2659 - loss: 2.0480
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2660 - loss: 2.0474
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2660 - loss: 2.0468
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0463
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2662 - loss: 2.0458
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2663 - loss: 2.0452
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2664 - loss: 2.0446
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2664 - loss: 2.0441
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2665 - loss: 2.0437
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2665 - loss: 2.0432
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2665 - loss: 2.0428
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2666 - loss: 2.0423
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2666 - loss: 2.0419
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2667 - loss: 2.0415
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2667 - loss: 2.0411
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2668 - loss: 2.0408
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2669 - loss: 2.0406
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2669 - loss: 2.0402
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2670 - loss: 2.0399
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2670 - loss: 2.0396
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2671 - loss: 2.0393
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2672 - loss: 2.0391
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2672 - loss: 2.0388
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2673 - loss: 2.0386 - val_accuracy: 0.2790 - val_loss: 1.9152
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8012
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9655  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2903 - loss: 1.9734
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2875 - loss: 1.9769
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2848 - loss: 1.9823
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2833 - loss: 1.9866
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2815 - loss: 1.9906
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 1.9938
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 1.9947
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 1.9947
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 1.9957
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 1.9965
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 1.9967
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9969
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 1.9968
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 1.9966
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 1.9963
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2811 - loss: 1.9961
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 1.9958
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9955
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2817 - loss: 1.9950
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 1.9943
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 1.9936
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2825 - loss: 1.9931
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 1.9925
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9920
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9916
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 1.9912
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2836 - loss: 1.9909
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 1.9905
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2841 - loss: 1.9900
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2843 - loss: 1.9897
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 1.9893
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 1.9890
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 1.9887
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 1.9884
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 1.9882
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 1.9880
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 1.9878
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 1.9877
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 1.9875
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 1.9873
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 1.9871
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 1.9869
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 1.9867
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2856 - loss: 1.9867 - val_accuracy: 0.2607 - val_loss: 1.9663
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.7918
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3155 - loss: 1.9462  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3112 - loss: 1.9407
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3078 - loss: 1.9362
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3042 - loss: 1.9358
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3024 - loss: 1.9371
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9387
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2989 - loss: 1.9398
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 1.9402
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9400
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9401
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9403
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9404
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 1.9410
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 1.9418
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 1.9426
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2928 - loss: 1.9431
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 1.9435
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2922 - loss: 1.9439
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2920 - loss: 1.9444
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9447
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2915 - loss: 1.9449
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 1.9451
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2913 - loss: 1.9453
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2912 - loss: 1.9455
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2911 - loss: 1.9458
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9459
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9461
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9463
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2909 - loss: 1.9465
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9466
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9467
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9469
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9470
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2911 - loss: 1.9471
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2911 - loss: 1.9472
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2912 - loss: 1.9473
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2912 - loss: 1.9473
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2913 - loss: 1.9473
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2913 - loss: 1.9474
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2913 - loss: 1.9474
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 1.9474
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 1.9474
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2915 - loss: 1.9474
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2915 - loss: 1.9474
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2916 - loss: 1.9474
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2916 - loss: 1.9474 - val_accuracy: 0.3238 - val_loss: 1.8688
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.6760
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3243 - loss: 1.8799  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3129 - loss: 1.9067
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3128 - loss: 1.9196
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 1.9267
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 1.9289
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3087 - loss: 1.9287
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3081 - loss: 1.9288
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3076 - loss: 1.9297
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3069 - loss: 1.9302
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9318
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 1.9329
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9333
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9332
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 1.9333
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 1.9333
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 1.9331
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 1.9328
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 1.9324
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 1.9320
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 1.9317
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 1.9315
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 1.9312
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 1.9310
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 1.9309
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 1.9308
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3042 - loss: 1.9308
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9307
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9306
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9306
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 1.9306
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9306
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9306
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9305
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9304
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 1.9303
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 1.9301
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 1.9300
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 1.9298
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 1.9296
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 1.9294
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 1.9291
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 1.9290
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 1.9288
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 1.9287
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3034 - loss: 1.9287 - val_accuracy: 0.3203 - val_loss: 1.8124
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.7303
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2860 - loss: 1.8613  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3058 - loss: 1.8542
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3103 - loss: 1.8550
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3131 - loss: 1.8554
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3140 - loss: 1.8572
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3144 - loss: 1.8580
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 1.8590
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8596
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.8596
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.8601
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.8604
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.8609
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.8615
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.8619
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.8622
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.8626
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.8630
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.8634
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.8637
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.8639
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.8641
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.8643
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 1.8645
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8649
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8653
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3135 - loss: 1.8658
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3135 - loss: 1.8663
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8670
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8675
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8679
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8683
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8687
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8690
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8693
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8695
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8697
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8699
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3135 - loss: 1.8701
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3135 - loss: 1.8703
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3135 - loss: 1.8704
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3136 - loss: 1.8705
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3136 - loss: 1.8707
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.8709
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.8710
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3137 - loss: 1.8712 - val_accuracy: 0.3434 - val_loss: 1.8152
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1817
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2732 - loss: 2.0774  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2822 - loss: 2.0171
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2884 - loss: 1.9886
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2916 - loss: 1.9696
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2931 - loss: 1.9613
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9546
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 1.9493
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9450
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9420
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 1.9394
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9364
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 1.9333
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3023 - loss: 1.9306
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3031 - loss: 1.9281
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9256
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 1.9235
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 1.9212
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9194
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3073 - loss: 1.9175
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 1.9155
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 1.9137
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 1.9120
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 1.9107
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 1.9095
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.9084
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 1.9071
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 1.9059
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 1.9047
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3132 - loss: 1.9036
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3135 - loss: 1.9027
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3139 - loss: 1.9016
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 1.9008
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 1.9000
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3148 - loss: 1.8992
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3150 - loss: 1.8985
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 1.8977
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.8970
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3160 - loss: 1.8962
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3162 - loss: 1.8955
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8949
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8942
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8937
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8931
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8926
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8926 - val_accuracy: 0.3304 - val_loss: 1.7881
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 2.1871
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9802  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3342 - loss: 1.9354
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3388 - loss: 1.9084
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3398 - loss: 1.9009
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8947
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3373 - loss: 1.8904
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8865
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3349 - loss: 1.8836
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8819
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3330 - loss: 1.8807
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8793
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8778
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8765
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8750
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8733
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8718
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8705
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8690
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8675
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8663
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8651
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 1.8640
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 1.8630
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 1.8622
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.8613
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.8605
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3321 - loss: 1.8598
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3322 - loss: 1.8590
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3324 - loss: 1.8582
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3325 - loss: 1.8573
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3326 - loss: 1.8566
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3328 - loss: 1.8559
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3329 - loss: 1.8552
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3330 - loss: 1.8545
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3332 - loss: 1.8538
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3333 - loss: 1.8531
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3334 - loss: 1.8525
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8519
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8513
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3337 - loss: 1.8508
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3337 - loss: 1.8503
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8498
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8494
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8489
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8486 - val_accuracy: 0.3521 - val_loss: 1.7951
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0460
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3121 - loss: 1.9156  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8978
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3184 - loss: 1.8877
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3219 - loss: 1.8740
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3243 - loss: 1.8620
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8530
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8448
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8402
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8364
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3303 - loss: 1.8348
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3304 - loss: 1.8333
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 1.8318
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8303
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8291
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 1.8281
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.8272
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3330 - loss: 1.8267
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3334 - loss: 1.8262
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8257
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8251
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8245
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8240
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3350 - loss: 1.8235
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3352 - loss: 1.8232
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8229
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3355 - loss: 1.8228
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8228
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8229
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8229
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8230
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8230
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8230
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8229
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8228
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8229
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8229
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8230
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8230
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8230
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8231
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8231
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8231
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8230
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8230
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8230 - val_accuracy: 0.3341 - val_loss: 1.7811
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.5625 - loss: 2.1147
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4520 - loss: 1.7781  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4122 - loss: 1.7704
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3913 - loss: 1.7771
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3807 - loss: 1.7797
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7811
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7832
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7855
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7870
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7874
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7876
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7881
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7883
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7884
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7885
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7884
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7883
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3557 - loss: 1.7881
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3556 - loss: 1.7878
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7875
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7872
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7869
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7867
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7867
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7867
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7867
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3541 - loss: 1.7867
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7868
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7869
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7871
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7873
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3532 - loss: 1.7875
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3531 - loss: 1.7876
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3531 - loss: 1.7876
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3530 - loss: 1.7877
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3530 - loss: 1.7877
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3528 - loss: 1.7877
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3527 - loss: 1.7877
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7877
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3525 - loss: 1.7877
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7877
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7878
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3522 - loss: 1.7878
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3521 - loss: 1.7879
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7880 - val_accuracy: 0.3573 - val_loss: 1.7740
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7255
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3761 - loss: 1.7213  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7179
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7228
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3704 - loss: 1.7288
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7313
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7366
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7421
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7456
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7486
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7505
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7524
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7546
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7568
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7586
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7602
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7615
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7624
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7630
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7632
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7632
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7632
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7633
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7633
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7633
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7632
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7632
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7632
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7633
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7634
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7635
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7637
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7639
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7641
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7643
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7645
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7647
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7649
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7650
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7650
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7651
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7651
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7652
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7652
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7652
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7652 - val_accuracy: 0.3628 - val_loss: 1.7840
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0786
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3744 - loss: 1.7259  
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7220
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7271
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7262
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7229
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7208
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7190
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7183
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7171
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7162
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7160
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7160
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7161
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7159
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7157
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7158
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3617 - loss: 1.7158
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7159
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7160
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7162
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7165
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7168
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7170
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7172
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7175
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7180
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7184
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7189
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7194
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7200
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7206
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7212
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7218
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7223
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7228
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7233
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7238
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7242
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7246
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7250
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7253
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7257
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7262
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7266
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7269
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7269 - val_accuracy: 0.3700 - val_loss: 1.7896
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3750 - loss: 1.6388
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7850  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3799 - loss: 1.7461
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3822 - loss: 1.7288
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3825 - loss: 1.7237
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3811 - loss: 1.7221
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3803 - loss: 1.7208
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3795 - loss: 1.7203
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7198
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3788 - loss: 1.7194
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.7190
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.7186
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3788 - loss: 1.7181
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7175
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3792 - loss: 1.7172
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7170
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3790 - loss: 1.7167
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3790 - loss: 1.7163
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3788 - loss: 1.7160
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3787 - loss: 1.7155
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.7152
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.7150
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7151
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.7152
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3776 - loss: 1.7153
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3773 - loss: 1.7153
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3770 - loss: 1.7153
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7153
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.7154
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3761 - loss: 1.7155
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3758 - loss: 1.7156
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.7159
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7163
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3750 - loss: 1.7166
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3748 - loss: 1.7170
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3746 - loss: 1.7173
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3744 - loss: 1.7177
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7180
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3740 - loss: 1.7183
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3739 - loss: 1.7185
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3737 - loss: 1.7188
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7190
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7192
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3732 - loss: 1.7194
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7196
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3730 - loss: 1.7197 - val_accuracy: 0.3654 - val_loss: 1.7983
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.5011
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7051  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7120
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7146
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3766 - loss: 1.7203
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3766 - loss: 1.7240
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3757 - loss: 1.7261
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3749 - loss: 1.7280
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3744 - loss: 1.7284
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3740 - loss: 1.7291
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7297
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3732 - loss: 1.7294
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7294
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7293
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7290
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7286
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7283
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7282
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7282
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7282
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7281
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7280
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7280
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7280
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7281
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3701 - loss: 1.7280
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7279
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7278
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7277
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7276
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7273
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7270
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7267
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7263
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7258
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7254
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7251
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7247
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7243
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7239
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3700 - loss: 1.7236
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3700 - loss: 1.7232
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3701 - loss: 1.7228
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3701 - loss: 1.7225
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7224 - val_accuracy: 0.3702 - val_loss: 1.7865

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:34[0m 1s/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:29:35.225737: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:41[0m 1s/step
[1m 54/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 957us/step
[1m110/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 931us/step
[1m166/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 922us/step
[1m221/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 923us/step
[1m271/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 939us/step
[1m325/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 939us/step
[1m387/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 920us/step
[1m445/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 914us/step
[1m505/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 905us/step
[1m564/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 899us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 50/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m108/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 944us/step
[1m167/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 913us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 37.98 [%]
Global F1 score (validation) = 34.92 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.23074791 0.21638869 0.19684677 ... 0.00586727 0.16652495 0.04977786]
 [0.22253846 0.25714368 0.19916612 ... 0.00210317 0.1547933  0.01166036]
 [0.20589514 0.20749271 0.18262932 ... 0.01142656 0.15544191 0.03096481]
 ...
 [0.1433781  0.20634465 0.12361723 ... 0.00699475 0.10379764 0.00431407]
 [0.15370244 0.22726384 0.1262611  ... 0.00467859 0.09888384 0.00671507]
 [0.19327961 0.25430572 0.16542028 ... 0.00406323 0.13445    0.00883813]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 45.3 [%]
Global accuracy score (test) = 32.23 [%]
Global F1 score (train) = 42.45 [%]
Global F1 score (test) = 30.17 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.12      0.09      0.10       184
 CAMINAR CON MÓVIL O LIBRO       0.19      0.51      0.27       184
       CAMINAR USUAL SPEED       0.14      0.02      0.04       184
            CAMINAR ZIGZAG       0.53      0.44      0.48       184
          DE PIE BARRIENDO       0.31      0.41      0.35       184
   DE PIE DOBLANDO TOALLAS       0.37      0.23      0.29       184
    DE PIE MOVIENDO LIBROS       0.30      0.42      0.35       184
          DE PIE USANDO PC       0.30      0.55      0.39       184
        FASE REPOSO CON K5       0.68      0.51      0.58       184
INCREMENTAL CICLOERGOMETRO       0.69      0.52      0.59       184
           SENTADO LEYENDO       0.33      0.40      0.36       184
         SENTADO USANDO PC       0.23      0.31      0.26       184
      SENTADO VIENDO LA TV       0.00      0.00      0.00       184
   SUBIR Y BAJAR ESCALERAS       0.30      0.07      0.11       184
                    TROTAR       0.32      0.36      0.34       161

                  accuracy                           0.32      2737
                 macro avg       0.32      0.32      0.30      2737
              weighted avg       0.32      0.32      0.30      2737


Accuracy capturado en la ejecución 7: 32.23 [%]
F1-score capturado en la ejecución 7: 30.17 [%]

=== EJECUCIÓN 8 ===

--- TRAIN (ejecución 8) ---

--- TEST (ejecución 8) ---
2025-10-31 15:29:48.416323: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:29:48.427960: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761920988.441537 1666465 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761920988.445981 1666465 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761920988.456159 1666465 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920988.456184 1666465 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920988.456186 1666465 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761920988.456187 1666465 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:29:48.459492: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761920990.837846 1666465 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761920993.939442 1666595 service.cc:152] XLA service 0x71982801c490 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761920993.939477 1666595 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:29:54.006528: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761920994.425107 1666595 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761920997.058796 1666595 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46:02[0m 5s/step - accuracy: 0.0625 - loss: 3.0965
[1m  19/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0832 - loss: 3.2056    
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0790 - loss: 3.2212
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0781 - loss: 3.2481
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0792 - loss: 3.2589
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0803 - loss: 3.2592
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0808 - loss: 3.2567
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0813 - loss: 3.2535
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0820 - loss: 3.2469
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0826 - loss: 3.2388
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0836 - loss: 3.2294
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0843 - loss: 3.2195
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0849 - loss: 3.2109
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0856 - loss: 3.2018
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0861 - loss: 3.1934
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0868 - loss: 3.1843
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0874 - loss: 3.1759
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0881 - loss: 3.1676
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0888 - loss: 3.1596
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0897 - loss: 3.1515
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0903 - loss: 3.1450
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0911 - loss: 3.1381
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0918 - loss: 3.1313
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0925 - loss: 3.1239
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0932 - loss: 3.1170
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0938 - loss: 3.1111
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0944 - loss: 3.1043
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0951 - loss: 3.0974
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0957 - loss: 3.0911
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0963 - loss: 3.0851
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0970 - loss: 3.0789
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0976 - loss: 3.0725
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0983 - loss: 3.0667
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0989 - loss: 3.0608
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0995 - loss: 3.0548
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1000 - loss: 3.0496
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1006 - loss: 3.0442
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1011 - loss: 3.0390
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1016 - loss: 3.0338
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1022 - loss: 3.0288
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1026 - loss: 3.0242
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1030 - loss: 3.0201
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1036 - loss: 3.0151
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1041 - loss: 3.0103
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1046 - loss: 3.0055
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1047 - loss: 3.0041
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1047 - loss: 3.0039 - val_accuracy: 0.1645 - val_loss: 2.3131
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1250 - loss: 2.7929
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1893 - loss: 2.5254  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1781 - loss: 2.5206
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1701 - loss: 2.5230
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1665 - loss: 2.5229
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1641 - loss: 2.5214
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1625 - loss: 2.5201
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1612 - loss: 2.5195
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1599 - loss: 2.5194
[1m 226/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1589 - loss: 2.5188
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1584 - loss: 2.5177
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1580 - loss: 2.5166
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1576 - loss: 2.5159
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1571 - loss: 2.5149
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1568 - loss: 2.5140
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1565 - loss: 2.5130
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1563 - loss: 2.5120
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1560 - loss: 2.5113
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1557 - loss: 2.5104
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1555 - loss: 2.5095
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1553 - loss: 2.5085
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1552 - loss: 2.5076
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1551 - loss: 2.5068
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1551 - loss: 2.5057
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1551 - loss: 2.5046
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1551 - loss: 2.5035
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1551 - loss: 2.5023
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1551 - loss: 2.5013
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1552 - loss: 2.5000
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1552 - loss: 2.4989
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1553 - loss: 2.4977
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1553 - loss: 2.4966
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4957
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4946
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4936
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4927
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4916
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4906
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4897
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4887
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4878
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4868
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4859
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4851
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4843
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4835
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4830 - val_accuracy: 0.1747 - val_loss: 2.1865
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0385
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1982 - loss: 2.2847  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1859 - loss: 2.3057
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1809 - loss: 2.3179
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1784 - loss: 2.3256
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1768 - loss: 2.3318
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1749 - loss: 2.3358
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1735 - loss: 2.3397
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1728 - loss: 2.3421
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1720 - loss: 2.3446
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1713 - loss: 2.3467
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1708 - loss: 2.3482
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1701 - loss: 2.3493
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1696 - loss: 2.3501
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1694 - loss: 2.3505
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1691 - loss: 2.3507
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1688 - loss: 2.3507
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1686 - loss: 2.3510
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1685 - loss: 2.3513
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3514
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1683 - loss: 2.3514
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1682 - loss: 2.3513
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1682 - loss: 2.3511
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3508
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1682 - loss: 2.3505
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1682 - loss: 2.3501
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1683 - loss: 2.3497
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1683 - loss: 2.3494
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3491
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3487
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1685 - loss: 2.3484
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1686 - loss: 2.3480
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1687 - loss: 2.3475
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1687 - loss: 2.3470
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1688 - loss: 2.3467
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1688 - loss: 2.3463
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1689 - loss: 2.3459
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1689 - loss: 2.3456
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1689 - loss: 2.3452
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1690 - loss: 2.3449
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1690 - loss: 2.3445
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1691 - loss: 2.3441
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1691 - loss: 2.3437
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3434
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3430
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1693 - loss: 2.3426
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1693 - loss: 2.3426 - val_accuracy: 0.1882 - val_loss: 2.1318
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.0464
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1627 - loss: 2.3277  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1768 - loss: 2.3290
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1808 - loss: 2.3185
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1823 - loss: 2.3085
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1835 - loss: 2.3054
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1837 - loss: 2.3034
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1840 - loss: 2.3022
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.3026
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1833 - loss: 2.3028
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1830 - loss: 2.3028
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.3027
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.3023
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.3018
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.3010
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.3004
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1830 - loss: 2.2996
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1832 - loss: 2.2984
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1833 - loss: 2.2970
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2957
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2943
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1838 - loss: 2.2930
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2921
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1840 - loss: 2.2910
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1842 - loss: 2.2900
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1843 - loss: 2.2890
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2881
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2873
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.2865
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2858
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2849
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2841
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2834
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2825
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2818
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.2810
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.2803
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.2795
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2788
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1865 - loss: 2.2781
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1866 - loss: 2.2774
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1868 - loss: 2.2767
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1869 - loss: 2.2761
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1869 - loss: 2.2755
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1870 - loss: 2.2749
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1871 - loss: 2.2744
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1871 - loss: 2.2742 - val_accuracy: 0.2174 - val_loss: 2.0932
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.4164
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2120 - loss: 2.2609  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2104 - loss: 2.2502
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2124 - loss: 2.2461
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2138 - loss: 2.2442
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2143 - loss: 2.2403
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2140 - loss: 2.2369
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2132 - loss: 2.2340
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.2311
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2118 - loss: 2.2284
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2113 - loss: 2.2264
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2107 - loss: 2.2249
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2103 - loss: 2.2235
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2101 - loss: 2.2223
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2098 - loss: 2.2212
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2097 - loss: 2.2201
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.2192
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2095 - loss: 2.2185
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2094 - loss: 2.2177
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2094 - loss: 2.2170
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2095 - loss: 2.2164
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.2157
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2097 - loss: 2.2152
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2098 - loss: 2.2147
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2098 - loss: 2.2143
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2099 - loss: 2.2140
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2100 - loss: 2.2136
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2101 - loss: 2.2131
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2102 - loss: 2.2127
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2102 - loss: 2.2122
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2103 - loss: 2.2117
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2104 - loss: 2.2111
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2105 - loss: 2.2106
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2106 - loss: 2.2100
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2107 - loss: 2.2095
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2108 - loss: 2.2090
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2108 - loss: 2.2086
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2109 - loss: 2.2082
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2109 - loss: 2.2078
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.2074
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.2070
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2111 - loss: 2.2066
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2111 - loss: 2.2061
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.2057
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2113 - loss: 2.2052
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2113 - loss: 2.2052 - val_accuracy: 0.2640 - val_loss: 2.0363
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0132
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1538  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2347 - loss: 2.1420
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2379 - loss: 2.1346
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2391 - loss: 2.1350
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2401 - loss: 2.1358
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2400 - loss: 2.1388
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2393 - loss: 2.1412
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2387 - loss: 2.1423
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2386 - loss: 2.1429
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2385 - loss: 2.1429
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2384 - loss: 2.1431
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.1438
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2380 - loss: 2.1441
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.1443
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2376 - loss: 2.1447
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1451
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2370 - loss: 2.1452
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2368 - loss: 2.1454
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2367 - loss: 2.1454
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2366 - loss: 2.1453
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2365 - loss: 2.1452
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.1451
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.1449
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2363 - loss: 2.1446
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2362 - loss: 2.1444
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2361 - loss: 2.1441
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2361 - loss: 2.1438
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2361 - loss: 2.1436
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2361 - loss: 2.1434
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2362 - loss: 2.1432
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2362 - loss: 2.1429
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2362 - loss: 2.1427
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2363 - loss: 2.1423
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2364 - loss: 2.1419
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2364 - loss: 2.1416
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2365 - loss: 2.1412
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2365 - loss: 2.1409
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2365 - loss: 2.1406
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2365 - loss: 2.1403
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2366 - loss: 2.1399
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2367 - loss: 2.1396
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2367 - loss: 2.1392
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2368 - loss: 2.1389
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2368 - loss: 2.1386
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2369 - loss: 2.1383 - val_accuracy: 0.2339 - val_loss: 2.0133
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0278
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2534 - loss: 2.0725  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2586 - loss: 2.0672
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2626 - loss: 2.0638
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2646 - loss: 2.0619
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2635 - loss: 2.0649
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2626 - loss: 2.0685
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.0716
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0740
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0755
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.0763
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2623 - loss: 2.0766
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2626 - loss: 2.0766
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0763
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2635 - loss: 2.0761
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2639 - loss: 2.0757
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.0758
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.0759
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0759
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2642 - loss: 2.0758
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2643 - loss: 2.0756
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2643 - loss: 2.0756
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2642 - loss: 2.0754
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2642 - loss: 2.0753
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2642 - loss: 2.0752
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0749
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0746
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0743
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0741
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0739
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2640 - loss: 2.0737
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2639 - loss: 2.0735
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0734
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0732
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0730
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2637 - loss: 2.0729
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2637 - loss: 2.0727
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2636 - loss: 2.0726
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2636 - loss: 2.0726
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2635 - loss: 2.0725
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0724
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0724
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0723
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0721
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0720
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0718 - val_accuracy: 0.3286 - val_loss: 1.8985
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.6491
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2653 - loss: 2.0373  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2716 - loss: 2.0442
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0434
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2697 - loss: 2.0440
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2674 - loss: 2.0459
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2656 - loss: 2.0468
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2647 - loss: 2.0471
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0470
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.0465
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0453
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0443
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.0431
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2643 - loss: 2.0415
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2646 - loss: 2.0406
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2649 - loss: 2.0398
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 2.0390
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2657 - loss: 2.0382
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0372
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2663 - loss: 2.0364
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2666 - loss: 2.0356
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2668 - loss: 2.0348
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.0342
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.0335
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.0327
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2677 - loss: 2.0320
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2679 - loss: 2.0312
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2681 - loss: 2.0306
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.0300
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2684 - loss: 2.0295
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.0290
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2686 - loss: 2.0285
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2687 - loss: 2.0280
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2688 - loss: 2.0276
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2690 - loss: 2.0272
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2691 - loss: 2.0267
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2692 - loss: 2.0262
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2693 - loss: 2.0258
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2694 - loss: 2.0254
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2696 - loss: 2.0250
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.0246
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.0242
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.0239
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.0236
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.0233
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2702 - loss: 2.0231 - val_accuracy: 0.3399 - val_loss: 1.8331
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.0625 - loss: 2.5198
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2475 - loss: 2.1557  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2585 - loss: 2.1153
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2653 - loss: 2.0910
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2697 - loss: 2.0756
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2736 - loss: 2.0657
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2767 - loss: 2.0570
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2792 - loss: 2.0490
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2809 - loss: 2.0438
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.0401
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 2.0372
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2830 - loss: 2.0342
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2838 - loss: 2.0312
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 2.0288
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.0263
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2854 - loss: 2.0239
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.0217
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.0194
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2868 - loss: 2.0174
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 2.0159
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2875 - loss: 2.0144
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 2.0126
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 2.0112
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2885 - loss: 2.0097
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.0083
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2890 - loss: 2.0070
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2893 - loss: 2.0057
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2894 - loss: 2.0047
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2896 - loss: 2.0037
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2898 - loss: 2.0028
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2899 - loss: 2.0019
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2899 - loss: 2.0012
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2899 - loss: 2.0003
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2900 - loss: 1.9995
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2901 - loss: 1.9986
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2902 - loss: 1.9978
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2903 - loss: 1.9970
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2904 - loss: 1.9963
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2904 - loss: 1.9957
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2905 - loss: 1.9951
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2906 - loss: 1.9945
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2907 - loss: 1.9939
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2908 - loss: 1.9933
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2909 - loss: 1.9927
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9922
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2911 - loss: 1.9916
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2911 - loss: 1.9914 - val_accuracy: 0.3567 - val_loss: 1.8262
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.8856
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2651 - loss: 1.9716  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2692 - loss: 1.9705
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2727 - loss: 1.9622
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2743 - loss: 1.9603
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2748 - loss: 1.9608
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2754 - loss: 1.9612
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 1.9613
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 1.9612
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 1.9617
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 1.9626
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 1.9632
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2773 - loss: 1.9632
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 1.9635
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2782 - loss: 1.9640
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2785 - loss: 1.9644
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 1.9649
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2792 - loss: 1.9652
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 1.9652
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 1.9651
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2809 - loss: 1.9648
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 1.9645
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2822 - loss: 1.9642
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 1.9639
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2834 - loss: 1.9635
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 1.9631
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2844 - loss: 1.9626
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 1.9620
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 1.9616
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 1.9612
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2863 - loss: 1.9607
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 1.9605
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2870 - loss: 1.9601
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2874 - loss: 1.9598
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 1.9595
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2880 - loss: 1.9592
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2884 - loss: 1.9588
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2887 - loss: 1.9585
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2891 - loss: 1.9582
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2894 - loss: 1.9578
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2898 - loss: 1.9575
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2901 - loss: 1.9571
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2904 - loss: 1.9568
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2908 - loss: 1.9565
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9563
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2913 - loss: 1.9560 - val_accuracy: 0.3502 - val_loss: 1.8145
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.9045
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8954  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3099 - loss: 1.9007
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3153 - loss: 1.8898
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8819
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3204 - loss: 1.8816
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8824
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8840
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8852
[1m 223/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8867
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 1.8887
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 1.8901
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 1.8908
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 1.8912
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 1.8920
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 1.8927
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 1.8929
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 1.8930
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 1.8930
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 1.8927
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 1.8925
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 1.8923
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 1.8921
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 1.8920
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 1.8920
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3154 - loss: 1.8920
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3155 - loss: 1.8921
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3157 - loss: 1.8921
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3157 - loss: 1.8921
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3159 - loss: 1.8922
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3160 - loss: 1.8922
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3160 - loss: 1.8922
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3161 - loss: 1.8922
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3162 - loss: 1.8921
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3163 - loss: 1.8921
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3163 - loss: 1.8920
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3164 - loss: 1.8919
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8919
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8918
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8918
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3167 - loss: 1.8917
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3167 - loss: 1.8916
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8915
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8915
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8914
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8913 - val_accuracy: 0.3637 - val_loss: 1.7804
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.6262
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3078 - loss: 1.7672  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3084 - loss: 1.8048
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3124 - loss: 1.8149
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3151 - loss: 1.8227
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8283
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8359
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8422
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8473
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 1.8513
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8539
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8554
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8572
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3172 - loss: 1.8586
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8598
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8608
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8615
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8618
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8622
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8627
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 1.8631
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 1.8630
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 1.8628
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 1.8627
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3226 - loss: 1.8627
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 1.8628
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 1.8628
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 1.8628
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 1.8627
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8626
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8625
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8625
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8626
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 1.8626
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3250 - loss: 1.8627
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 1.8627
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3253 - loss: 1.8627
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 1.8627
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 1.8628
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 1.8628
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 1.8627
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 1.8627
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8627
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 1.8626
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3261 - loss: 1.8626
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3261 - loss: 1.8626 - val_accuracy: 0.3593 - val_loss: 1.7739
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.5471
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3865 - loss: 1.7800  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7877
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7907
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7996
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3471 - loss: 1.8059
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3449 - loss: 1.8122
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.8162
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3430 - loss: 1.8192
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3421 - loss: 1.8224
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8259
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8283
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3408 - loss: 1.8304
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8315
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8323
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8328
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8332
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8337
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8341
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8344
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8348
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8351
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8353
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8354
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8357
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8358
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8359
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8361
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.8363
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.8363
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8364
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3373 - loss: 1.8364
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8363
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8364
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8364
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8364
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8364
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8364
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8364
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8363
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8362
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8361
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8360
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3373 - loss: 1.8358
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3373 - loss: 1.8357
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8356 - val_accuracy: 0.3591 - val_loss: 1.7763
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.8457
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9047  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3199 - loss: 1.8553
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3274 - loss: 1.8354
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3324 - loss: 1.8252
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3346 - loss: 1.8216
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3356 - loss: 1.8200
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8186
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8175
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8163
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8157
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8153
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8152
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8156
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8162
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8169
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8174
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8178
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8182
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 1.8186
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8188
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8187
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8186
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8184
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8181
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8179
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8176
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3355 - loss: 1.8173
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3356 - loss: 1.8170
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8167
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8164
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8162
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8159
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8157
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8156
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8153
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8150
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3368 - loss: 1.8147
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3369 - loss: 1.8145
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8142
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8140
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8138
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.8136
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.8135
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3378 - loss: 1.8132
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8131 - val_accuracy: 0.3839 - val_loss: 1.7649
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0015
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3926 - loss: 1.7377  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3874 - loss: 1.7359
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3801 - loss: 1.7462
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7515
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3737 - loss: 1.7556
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7593
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7617
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7632
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3677 - loss: 1.7645
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7662
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7676
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7686
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7691
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7695
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7702
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7712
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7722
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7728
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7735
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7743
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7750
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7753
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7756
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7758
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7760
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7762
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7764
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7766
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7768
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3559 - loss: 1.7770
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3557 - loss: 1.7771
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3555 - loss: 1.7772
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7772
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7772
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7772
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7772
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7773
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7773
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7773
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7772
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3540 - loss: 1.7772
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7772
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7772
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7771
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7770
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7770 - val_accuracy: 0.3774 - val_loss: 1.7671
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.8177
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3583 - loss: 1.8766  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3579 - loss: 1.8684
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3559 - loss: 1.8514
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3568 - loss: 1.8376
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3576 - loss: 1.8242
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3586 - loss: 1.8140
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.8074
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.8013
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7958
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7916
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7884
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7857
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7835
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7818
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7801
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7785
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7771
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7759
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7748
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7739
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7731
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7723
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7716
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7707
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7701
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7696
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7691
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7687
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7684
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7680
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7677
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7673
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7670
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7667
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7663
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7659
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7654
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7651
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7648
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7644
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7641
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7639
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7637
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7634
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7632 - val_accuracy: 0.3782 - val_loss: 1.7681
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1664
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3143 - loss: 1.8666  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3298 - loss: 1.8319
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8066
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3472 - loss: 1.7929
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7824
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7771
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7737
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3556 - loss: 1.7713
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7689
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7674
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7655
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7642
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7623
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7603
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7586
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7572
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7559
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7548
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7540
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7535
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7529
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7523
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7517
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7509
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7502
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7497
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7491
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7486
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7481
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7478
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7473
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7468
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7463
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7459
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7456
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7452
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7449
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7446
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7443
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7441
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7438
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7435
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7433
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7430
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7428 - val_accuracy: 0.3804 - val_loss: 1.7677
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8121
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3144 - loss: 1.7412  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3310 - loss: 1.7547
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3381 - loss: 1.7687
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3426 - loss: 1.7738
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3470 - loss: 1.7717
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.7689
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7671
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3540 - loss: 1.7648
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7617
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7585
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7552
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7522
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7492
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7465
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7441
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7418
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7403
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7391
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7378
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7363
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7352
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3672 - loss: 1.7342
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7332
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7321
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7310
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7300
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3701 - loss: 1.7291
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7282
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7273
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7265
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7258
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7253
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7248
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7244
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3726 - loss: 1.7240
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7236
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7233
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3730 - loss: 1.7230
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7227
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7225
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7222
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7220
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7218
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3736 - loss: 1.7217 - val_accuracy: 0.3734 - val_loss: 1.7752
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9623
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3513 - loss: 1.6524  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3722 - loss: 1.6336
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3750 - loss: 1.6445
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3744 - loss: 1.6566
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3741 - loss: 1.6667
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3733 - loss: 1.6745
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3721 - loss: 1.6798
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.6836
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3711 - loss: 1.6863
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.6887
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3717 - loss: 1.6904
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3721 - loss: 1.6916
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3725 - loss: 1.6923
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3729 - loss: 1.6926
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3732 - loss: 1.6930
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.6932
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.6936
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.6941
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3734 - loss: 1.6945
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.6946
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.6948
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.6951
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.6953
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.6954
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.6956
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3735 - loss: 1.6956
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3736 - loss: 1.6956
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3737 - loss: 1.6955
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3739 - loss: 1.6953
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3740 - loss: 1.6951
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.6950
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.6950
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3742 - loss: 1.6950
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3743 - loss: 1.6949
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3744 - loss: 1.6948
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3745 - loss: 1.6947
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3746 - loss: 1.6947
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3747 - loss: 1.6946
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3748 - loss: 1.6947
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3749 - loss: 1.6947
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3749 - loss: 1.6948
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3750 - loss: 1.6949
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3750 - loss: 1.6950
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3750 - loss: 1.6950
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.6951
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3751 - loss: 1.6951 - val_accuracy: 0.3800 - val_loss: 1.7646
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1875 - loss: 1.9255
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3315 - loss: 1.7532  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3504 - loss: 1.7424
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7368
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7349
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7320
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7286
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7259
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3687 - loss: 1.7215
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7193
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7169
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7146
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7129
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7114
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3732 - loss: 1.7094
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3739 - loss: 1.7077
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3747 - loss: 1.7060
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7048
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3758 - loss: 1.7038
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3762 - loss: 1.7031
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3766 - loss: 1.7024
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3770 - loss: 1.7017
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7011
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3779 - loss: 1.7004
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.6997
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3788 - loss: 1.6991
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3793 - loss: 1.6983
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3797 - loss: 1.6977
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3801 - loss: 1.6970
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3804 - loss: 1.6966
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3807 - loss: 1.6961
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6958
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3812 - loss: 1.6956
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3815 - loss: 1.6953
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3816 - loss: 1.6950
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6947
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6945
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3821 - loss: 1.6943
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6940
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3824 - loss: 1.6938
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6936
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6934
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3827 - loss: 1.6932
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3829 - loss: 1.6930
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6928
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6927 - val_accuracy: 0.3743 - val_loss: 1.7915
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.5000 - loss: 1.3744
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4031 - loss: 1.5611  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3981 - loss: 1.5975
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3972 - loss: 1.6155
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6260
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3958 - loss: 1.6300
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3959 - loss: 1.6319
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6347
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3947 - loss: 1.6378
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3938 - loss: 1.6406
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3929 - loss: 1.6437
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3922 - loss: 1.6465
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3916 - loss: 1.6484
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3908 - loss: 1.6498
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3903 - loss: 1.6510
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3899 - loss: 1.6521
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3896 - loss: 1.6529
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3893 - loss: 1.6537
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3891 - loss: 1.6543
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3889 - loss: 1.6549
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3887 - loss: 1.6555
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3886 - loss: 1.6559
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3886 - loss: 1.6561
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3886 - loss: 1.6563
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3885 - loss: 1.6565
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3885 - loss: 1.6567
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3885 - loss: 1.6569
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3885 - loss: 1.6572
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3885 - loss: 1.6574
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3884 - loss: 1.6577
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3884 - loss: 1.6579
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3883 - loss: 1.6582
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3883 - loss: 1.6584
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3882 - loss: 1.6586
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3881 - loss: 1.6588
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3881 - loss: 1.6590
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3880 - loss: 1.6591
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6593
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6594
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6595
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6595
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6596
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3878 - loss: 1.6596
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3878 - loss: 1.6598
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3878 - loss: 1.6599
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3878 - loss: 1.6599 - val_accuracy: 0.3828 - val_loss: 1.7648

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:30[0m 1s/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 977us/step2025-10-31 15:31:01.925976: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:31[0m 1s/step
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m105/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 973us/step
[1m158/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 965us/step
[1m214/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 946us/step
[1m266/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 950us/step
[1m323/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 939us/step
[1m381/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 928us/step
[1m440/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 919us/step
[1m496/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 917us/step
[1m549/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 920us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m49/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 931us/step
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 924us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 37.02 [%]
Global F1 score (validation) = 34.87 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.18897209 0.25639504 0.20200683 ... 0.00904335 0.13468309 0.02486503]
 [0.15625185 0.25416765 0.16074575 ... 0.00573116 0.10200023 0.01081426]
 [0.2101031  0.16624843 0.20280166 ... 0.00197384 0.18684748 0.1355125 ]
 ...
 [0.15004803 0.24148324 0.15624669 ... 0.00733492 0.09855778 0.00898377]
 [0.19210179 0.22283618 0.23359652 ... 0.00152865 0.16675472 0.0193206 ]
 [0.13184582 0.21835093 0.13389172 ... 0.00659725 0.09003385 0.00734994]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 45.33 [%]
Global accuracy score (test) = 34.05 [%]
Global F1 score (train) = 43.06 [%]
Global F1 score (test) = 32.98 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.11      0.03      0.04       184
 CAMINAR CON MÓVIL O LIBRO       0.19      0.50      0.28       184
       CAMINAR USUAL SPEED       0.14      0.16      0.15       184
            CAMINAR ZIGZAG       0.55      0.31      0.40       184
          DE PIE BARRIENDO       0.34      0.40      0.37       184
   DE PIE DOBLANDO TOALLAS       0.24      0.09      0.13       184
    DE PIE MOVIENDO LIBROS       0.28      0.48      0.36       184
          DE PIE USANDO PC       0.34      0.49      0.40       184
        FASE REPOSO CON K5       0.98      0.59      0.74       184
INCREMENTAL CICLOERGOMETRO       0.74      0.52      0.61       184
           SENTADO LEYENDO       0.30      0.25      0.27       184
         SENTADO USANDO PC       0.24      0.29      0.26       184
      SENTADO VIENDO LA TV       0.42      0.45      0.43       184
   SUBIR Y BAJAR ESCALERAS       0.23      0.02      0.03       184
                    TROTAR       0.41      0.57      0.48       161

                  accuracy                           0.34      2737
                 macro avg       0.37      0.34      0.33      2737
              weighted avg       0.37      0.34      0.33      2737


Accuracy capturado en la ejecución 8: 34.05 [%]
F1-score capturado en la ejecución 8: 32.98 [%]

=== EJECUCIÓN 9 ===

--- TRAIN (ejecución 9) ---

--- TEST (ejecución 9) ---
2025-10-31 15:31:15.252089: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:31:15.263382: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761921075.276930 1669986 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761921075.281334 1669986 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761921075.291190 1669986 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921075.291212 1669986 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921075.291214 1669986 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921075.291216 1669986 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:31:15.294439: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761921077.671979 1669986 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761921080.805733 1670098 service.cc:152] XLA service 0x7a962401b010 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761921080.805771 1670098 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:31:20.869048: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761921081.291188 1670098 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761921083.928467 1670098 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:00[0m 6s/step - accuracy: 0.0625 - loss: 3.3869
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0555 - loss: 3.3662    
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0501 - loss: 3.3700
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0483 - loss: 3.3654
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0497 - loss: 3.3542
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0508 - loss: 3.3445
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0528 - loss: 3.3313
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0547 - loss: 3.3173
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0563 - loss: 3.3061
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0580 - loss: 3.2942
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0596 - loss: 3.2812
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0611 - loss: 3.2690
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0627 - loss: 3.2565
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0642 - loss: 3.2453
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0657 - loss: 3.2344
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0671 - loss: 3.2235
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0686 - loss: 3.2125
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0698 - loss: 3.2037
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0711 - loss: 3.1942
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0724 - loss: 3.1849
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0737 - loss: 3.1762
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0749 - loss: 3.1674
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0762 - loss: 3.1581
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0772 - loss: 3.1506
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0783 - loss: 3.1430
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0793 - loss: 3.1357
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0802 - loss: 3.1288
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0811 - loss: 3.1216
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0821 - loss: 3.1145
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0830 - loss: 3.1075
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0838 - loss: 3.1008
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0846 - loss: 3.0944
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0854 - loss: 3.0879
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0862 - loss: 3.0820
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0870 - loss: 3.0760
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0878 - loss: 3.0698
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0886 - loss: 3.0636
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0893 - loss: 3.0579
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0900 - loss: 3.0524
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0907 - loss: 3.0463
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0914 - loss: 3.0409
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0921 - loss: 3.0352
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0927 - loss: 3.0298
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0934 - loss: 3.0245
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0940 - loss: 3.0190
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.0944 - loss: 3.0158
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.0944 - loss: 3.0156 - val_accuracy: 0.1652 - val_loss: 2.3041
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.0625 - loss: 2.1298
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1079 - loss: 2.4875  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1265 - loss: 2.4854
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1345 - loss: 2.4908
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1375 - loss: 2.4963
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1396 - loss: 2.4994
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1411 - loss: 2.5012
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1424 - loss: 2.5020
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1433 - loss: 2.5021
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1439 - loss: 2.5020
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1444 - loss: 2.5014
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1448 - loss: 2.5008
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1450 - loss: 2.5003
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1452 - loss: 2.4997
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1455 - loss: 2.4987
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1458 - loss: 2.4978
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1462 - loss: 2.4968
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1464 - loss: 2.4956
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1468 - loss: 2.4943
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1470 - loss: 2.4931
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1473 - loss: 2.4917
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1476 - loss: 2.4901
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1480 - loss: 2.4885
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1483 - loss: 2.4870
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1485 - loss: 2.4857
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1486 - loss: 2.4846
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1488 - loss: 2.4835
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1489 - loss: 2.4824
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1489 - loss: 2.4815
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1490 - loss: 2.4806
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1491 - loss: 2.4796
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1492 - loss: 2.4787
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1493 - loss: 2.4778
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1494 - loss: 2.4769
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1495 - loss: 2.4760
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1496 - loss: 2.4751
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1497 - loss: 2.4740
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1498 - loss: 2.4730
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1499 - loss: 2.4721
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1500 - loss: 2.4712
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1502 - loss: 2.4702
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1503 - loss: 2.4692
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1505 - loss: 2.4682
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1507 - loss: 2.4672
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1508 - loss: 2.4663
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1509 - loss: 2.4658 - val_accuracy: 0.1787 - val_loss: 2.1980
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.2472
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1605 - loss: 2.4101  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1639 - loss: 2.4031
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1639 - loss: 2.3997
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3944
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3905
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1647 - loss: 2.3873
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1645 - loss: 2.3848
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1644 - loss: 2.3824
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1644 - loss: 2.3811
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1645 - loss: 2.3797
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1646 - loss: 2.3780
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1645 - loss: 2.3765
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1646 - loss: 2.3752
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1646 - loss: 2.3742
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1645 - loss: 2.3736
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1644 - loss: 2.3730
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1645 - loss: 2.3724
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1646 - loss: 2.3716
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1647 - loss: 2.3708
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3700
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3692
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1651 - loss: 2.3684
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3676
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1654 - loss: 2.3666
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1655 - loss: 2.3656
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1656 - loss: 2.3646
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1657 - loss: 2.3637
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1658 - loss: 2.3627
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1659 - loss: 2.3617
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1660 - loss: 2.3609
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1661 - loss: 2.3600
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1661 - loss: 2.3592
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1662 - loss: 2.3584
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1662 - loss: 2.3578
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1663 - loss: 2.3570
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1663 - loss: 2.3564
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1663 - loss: 2.3557
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1664 - loss: 2.3549
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1664 - loss: 2.3542
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1665 - loss: 2.3535
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1666 - loss: 2.3528
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1667 - loss: 2.3520
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3512
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1669 - loss: 2.3504
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1670 - loss: 2.3500 - val_accuracy: 0.2063 - val_loss: 2.1208
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3619
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1678 - loss: 2.2967  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1726 - loss: 2.2923
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1740 - loss: 2.2895
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1772 - loss: 2.2835
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1796 - loss: 2.2820
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1806 - loss: 2.2799
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.2779
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.2767
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1833 - loss: 2.2761
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2763
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2762
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2760
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1848 - loss: 2.2753
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2747
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2740
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2733
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2726
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2721
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2715
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2710
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2707
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2704
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2700
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2697
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2694
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2692
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1858 - loss: 2.2690
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.2687
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.2686
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.2684
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1861 - loss: 2.2682
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2680
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2679
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.2677
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1865 - loss: 2.2675
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1867 - loss: 2.2673
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1868 - loss: 2.2670
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1869 - loss: 2.2668
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1870 - loss: 2.2665
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1871 - loss: 2.2663
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1871 - loss: 2.2661
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1872 - loss: 2.2659
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1872 - loss: 2.2657
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1873 - loss: 2.2655
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1874 - loss: 2.2653 - val_accuracy: 0.2142 - val_loss: 2.0749
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4730
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1427 - loss: 2.2651  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1455 - loss: 2.2714
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1520 - loss: 2.2715
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1586 - loss: 2.2657
[1m 121/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1649 - loss: 2.2562
[1m 146/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1696 - loss: 2.2498
[1m 170/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1731 - loss: 2.2454
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1758 - loss: 2.2420
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1783 - loss: 2.2392
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1808 - loss: 2.2374
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2360
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2340
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2317
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2299
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1873 - loss: 2.2282
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1881 - loss: 2.2268
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1888 - loss: 2.2255
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1896 - loss: 2.2243
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1903 - loss: 2.2231
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1910 - loss: 2.2219
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1915 - loss: 2.2211
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1920 - loss: 2.2201
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1925 - loss: 2.2192
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1929 - loss: 2.2185
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1932 - loss: 2.2178
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1936 - loss: 2.2170
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1939 - loss: 2.2164
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1942 - loss: 2.2157
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1945 - loss: 2.2151
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1948 - loss: 2.2147
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1951 - loss: 2.2142
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1953 - loss: 2.2138
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1955 - loss: 2.2134
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1957 - loss: 2.2129
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1959 - loss: 2.2124
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1961 - loss: 2.2119
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1962 - loss: 2.2114
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1964 - loss: 2.2109
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1966 - loss: 2.2105
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1968 - loss: 2.2100
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1969 - loss: 2.2095
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1971 - loss: 2.2090
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1973 - loss: 2.2084
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1975 - loss: 2.2079
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1976 - loss: 2.2075
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1977 - loss: 2.2073 - val_accuracy: 0.2431 - val_loss: 2.0286
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9030
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2071 - loss: 2.1071  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2115 - loss: 2.1453
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2129 - loss: 2.1498
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1534
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2093 - loss: 2.1565
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2084 - loss: 2.1594
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2082 - loss: 2.1608
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2082 - loss: 2.1615
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2081 - loss: 2.1620
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2080 - loss: 2.1624
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2079 - loss: 2.1632
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2078 - loss: 2.1635
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2079 - loss: 2.1633
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2081 - loss: 2.1628
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2084 - loss: 2.1623
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1617
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2091 - loss: 2.1610
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2093 - loss: 2.1602
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.1595
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2099 - loss: 2.1588
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2102 - loss: 2.1582
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2104 - loss: 2.1577
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2106 - loss: 2.1574
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2108 - loss: 2.1571
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1569
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2111 - loss: 2.1567
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1563
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2113 - loss: 2.1560
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2115 - loss: 2.1558
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2116 - loss: 2.1555
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2118 - loss: 2.1551
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2119 - loss: 2.1548
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2121 - loss: 2.1544
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2123 - loss: 2.1539
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2124 - loss: 2.1535
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2126 - loss: 2.1531
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2127 - loss: 2.1527
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2129 - loss: 2.1524
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.1520
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.1517
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.1514
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2134 - loss: 2.1510
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2135 - loss: 2.1505
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2137 - loss: 2.1501
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2137 - loss: 2.1500 - val_accuracy: 0.2413 - val_loss: 2.0080
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.0082
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2322 - loss: 2.0077  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2395 - loss: 2.0318
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2390 - loss: 2.0445
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2386 - loss: 2.0515
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2378 - loss: 2.0609
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2371 - loss: 2.0665
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2373 - loss: 2.0696
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2374 - loss: 2.0716
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2374 - loss: 2.0732
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2375 - loss: 2.0744
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.0753
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2378 - loss: 2.0764
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2381 - loss: 2.0771
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2384 - loss: 2.0774
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2387 - loss: 2.0774
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2391 - loss: 2.0773
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2395 - loss: 2.0772
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2398 - loss: 2.0769
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2401 - loss: 2.0767
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2402 - loss: 2.0768
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2404 - loss: 2.0770
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2405 - loss: 2.0772
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.0775
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2409 - loss: 2.0777
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.0779
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2413 - loss: 2.0779
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2415 - loss: 2.0780
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.0781
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2418 - loss: 2.0783
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2420 - loss: 2.0784
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2422 - loss: 2.0785
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2423 - loss: 2.0786
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.0786
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.0785
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2428 - loss: 2.0785
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.0785
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.0785
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.0784
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.0784
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.0784
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2438 - loss: 2.0783
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2440 - loss: 2.0783
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2441 - loss: 2.0783
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2443 - loss: 2.0782
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2443 - loss: 2.0782 - val_accuracy: 0.2585 - val_loss: 1.9727
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.8117
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2593 - loss: 2.0732  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2523 - loss: 2.0668
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2524 - loss: 2.0570
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2524 - loss: 2.0535
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2530 - loss: 2.0546
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2548 - loss: 2.0536
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2565 - loss: 2.0511
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2575 - loss: 2.0493
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2583 - loss: 2.0475
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2588 - loss: 2.0461
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2596 - loss: 2.0451
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2605 - loss: 2.0439
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.0424
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2625 - loss: 2.0410
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0399
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.0389
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2647 - loss: 2.0381
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2653 - loss: 2.0376
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0370
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2662 - loss: 2.0367
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2666 - loss: 2.0365
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2669 - loss: 2.0363
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2673 - loss: 2.0359
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.0355
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.0350
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2682 - loss: 2.0344
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.0339
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2688 - loss: 2.0334
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2690 - loss: 2.0330
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2692 - loss: 2.0326
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.0321
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.0317
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.0313
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.0308
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.0303
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.0299
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0295
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0292
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0289
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0285
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0282
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.0279
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0276
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0273
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0271 - val_accuracy: 0.3438 - val_loss: 1.8371
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.7653
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3204 - loss: 1.9130  
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3015 - loss: 1.9377
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9484
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2935 - loss: 1.9484
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2919 - loss: 1.9501
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2907 - loss: 1.9528
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 1.9548
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2887 - loss: 1.9558
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2887 - loss: 1.9567
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2886 - loss: 1.9584
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 1.9607
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 1.9631
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2874 - loss: 1.9651
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2869 - loss: 1.9670
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 1.9688
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 1.9703
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2854 - loss: 1.9716
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 1.9727
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 1.9735
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 1.9740
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 1.9744
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 1.9747
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 1.9750
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 1.9754
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 1.9756
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 1.9759
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 1.9760
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 1.9761
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 1.9761
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 1.9761
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 1.9761
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 1.9761
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 1.9763
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 1.9763
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 1.9764
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 1.9765
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 1.9765
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 1.9765
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 1.9764
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 1.9764
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 1.9763
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 1.9762
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 1.9762
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 1.9760
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 1.9759
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2860 - loss: 1.9758 - val_accuracy: 0.3626 - val_loss: 1.8006
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8232
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2770 - loss: 1.9260  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2919 - loss: 1.9248
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9333
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2970 - loss: 1.9350
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2978 - loss: 1.9366
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9376
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 1.9373
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 1.9368
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 1.9364
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 1.9362
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9367
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2989 - loss: 1.9368
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9367
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9369
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9369
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2979 - loss: 1.9366
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2976 - loss: 1.9364
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 1.9364
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9365
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9366
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 1.9369
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 1.9371
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9373
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9373
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9374
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9374
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9373
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9372
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9370
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9367
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9365
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9361
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9358
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9356
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9353
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 1.9350
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9348
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2957 - loss: 1.9346
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2957 - loss: 1.9343
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2958 - loss: 1.9341
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 1.9338
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9335
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9333
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9331
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2961 - loss: 1.9329 - val_accuracy: 0.3591 - val_loss: 1.7708
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9133
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3106 - loss: 1.9601  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3032 - loss: 1.9394
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3019 - loss: 1.9267
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9168
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9102
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3022 - loss: 1.9039
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 1.8988
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 1.8959
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 1.8935
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 1.8917
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3032 - loss: 1.8902
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3034 - loss: 1.8894
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 1.8888
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 1.8885
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 1.8880
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 1.8876
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 1.8874
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 1.8872
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 1.8869
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 1.8866
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 1.8862
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 1.8859
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 1.8857
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 1.8856
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 1.8855
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 1.8854
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.8855
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.8855
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 1.8855
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 1.8855
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 1.8856
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 1.8857
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.8857
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.8858
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 1.8858
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 1.8859
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 1.8859
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3067 - loss: 1.8858
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 1.8858
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 1.8857
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 1.8857
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3073 - loss: 1.8856
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 1.8856
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3076 - loss: 1.8855
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3077 - loss: 1.8854 - val_accuracy: 0.3619 - val_loss: 1.7662
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.2500 - loss: 1.9420
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2698 - loss: 1.9503  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2785 - loss: 1.9410
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2822 - loss: 1.9308
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2859 - loss: 1.9209
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2900 - loss: 1.9111
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2928 - loss: 1.9047
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 1.8980
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 1.8932
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 1.8884
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 1.8847
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 1.8814
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 1.8788
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3086 - loss: 1.8771
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 1.8757
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8742
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 1.8728
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 1.8714
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 1.8700
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 1.8689
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 1.8680
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3154 - loss: 1.8672
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3159 - loss: 1.8664
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3163 - loss: 1.8658
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3167 - loss: 1.8651
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8645
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8639
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8635
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8631
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8629
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8627
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8624
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8623
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8621
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8619
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 1.8616
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 1.8614
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8611
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 1.8609
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 1.8608
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8606
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8605
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8604
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 1.8603
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 1.8602
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3205 - loss: 1.8602 - val_accuracy: 0.3502 - val_loss: 1.7712
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.1547
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3368 - loss: 1.8984  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8654
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3404 - loss: 1.8497
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8470
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8451
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8437
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8425
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8416
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8409
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8403
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8400
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8398
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3376 - loss: 1.8395
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3376 - loss: 1.8388
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3378 - loss: 1.8377
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8365
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8352
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.8339
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3386 - loss: 1.8328
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8319
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8310
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8302
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8295
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8289
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8283
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8278
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8275
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8274
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8273
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8272
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8271
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8271
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8271
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8272
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8274
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8274
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8275
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8276
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8276
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8277
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8277
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8278
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8279
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8279
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8280 - val_accuracy: 0.3673 - val_loss: 1.7381
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.0764
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8839  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3210 - loss: 1.8586
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3264 - loss: 1.8430
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3290 - loss: 1.8359
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8306
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8291
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3332 - loss: 1.8272
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8244
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8221
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3351 - loss: 1.8210
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3352 - loss: 1.8204
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 1.8196
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3358 - loss: 1.8186
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8173
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8161
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8152
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8143
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8133
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.8124
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3369 - loss: 1.8115
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8107
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8099
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3373 - loss: 1.8091
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8084
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3375 - loss: 1.8078
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.8072
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8066
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3378 - loss: 1.8061
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8055
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8050
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8045
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8041
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8037
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3386 - loss: 1.8032
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8028
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8024
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8020
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8016
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8013
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8010
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8008
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8005
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8002
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.7999
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.7997
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3395 - loss: 1.7996 - val_accuracy: 0.3719 - val_loss: 1.7366
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2265
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3755 - loss: 1.7929  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3553 - loss: 1.8020
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8055
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3457 - loss: 1.8039
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7993
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3455 - loss: 1.7950
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3466 - loss: 1.7899
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7862
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3481 - loss: 1.7835
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7815
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7804
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7800
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7797
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3484 - loss: 1.7798
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7798
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3486 - loss: 1.7798
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3486 - loss: 1.7796
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3487 - loss: 1.7792
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3489 - loss: 1.7786
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7780
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7772
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7766
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.7761
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7756
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3504 - loss: 1.7753
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3506 - loss: 1.7750
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3507 - loss: 1.7748
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3508 - loss: 1.7747
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3509 - loss: 1.7745
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3509 - loss: 1.7742
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7740
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7737
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3513 - loss: 1.7733
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3514 - loss: 1.7730
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3516 - loss: 1.7726
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.7723
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7719
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7716
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3521 - loss: 1.7713
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3522 - loss: 1.7710
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7708
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7707
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7706
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3525 - loss: 1.7706
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3525 - loss: 1.7705
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7705 - val_accuracy: 0.3578 - val_loss: 1.7721
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.7505
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3816 - loss: 1.6672  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3743 - loss: 1.6856
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7000
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7094
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7173
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7206
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3557 - loss: 1.7226
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7251
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7263
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3541 - loss: 1.7273
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3541 - loss: 1.7284
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7296
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7312
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7327
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7338
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7349
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7361
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7373
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7385
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7394
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7402
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7410
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7419
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7429
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7437
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7446
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7453
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7460
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3541 - loss: 1.7467
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3540 - loss: 1.7472
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7475
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7478
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7480
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7483
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7484
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7485
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7485
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7486
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7486
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7485
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7485
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7484
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7483
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7483
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7483 - val_accuracy: 0.3656 - val_loss: 1.7326
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 1.6089
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4042 - loss: 1.6434  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3973 - loss: 1.6489
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3881 - loss: 1.6661
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6770
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3804 - loss: 1.6834
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.6883
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.6891
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.6889
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.6883
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6877
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.6880
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6891
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3763 - loss: 1.6901
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3759 - loss: 1.6911
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3755 - loss: 1.6921
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3752 - loss: 1.6929
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3748 - loss: 1.6939
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3744 - loss: 1.6949
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3741 - loss: 1.6956
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3739 - loss: 1.6963
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3736 - loss: 1.6971
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3734 - loss: 1.6978
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3732 - loss: 1.6985
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3730 - loss: 1.6992
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3728 - loss: 1.6998
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3726 - loss: 1.7003
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7008
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7012
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7015
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3720 - loss: 1.7018
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7020
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7023
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7026
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7028
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7030
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7032
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7033
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7035
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7036
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7038
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7041
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7044
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7046
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7049
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7050 - val_accuracy: 0.3828 - val_loss: 1.7186
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.4500
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3751 - loss: 1.6481  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3821 - loss: 1.6519
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3800 - loss: 1.6696
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3801 - loss: 1.6810
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6852
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3804 - loss: 1.6891
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3804 - loss: 1.6898
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3803 - loss: 1.6909
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3808 - loss: 1.6910
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3813 - loss: 1.6908
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6910
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6911
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3823 - loss: 1.6914
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3823 - loss: 1.6920
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6926
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3821 - loss: 1.6933
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6941
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6945
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6947
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6946
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6946
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6946
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6947
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6948
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6950
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6951
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6953
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6956
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6958
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6959
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3817 - loss: 1.6960
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3817 - loss: 1.6961
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3816 - loss: 1.6961
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3815 - loss: 1.6961
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3815 - loss: 1.6961
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3814 - loss: 1.6961
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3814 - loss: 1.6961
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3813 - loss: 1.6961
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3813 - loss: 1.6961
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3813 - loss: 1.6962
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3812 - loss: 1.6962
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3812 - loss: 1.6963
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3811 - loss: 1.6965
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3811 - loss: 1.6966
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6968
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6968 - val_accuracy: 0.3641 - val_loss: 1.7719
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.8604
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7163  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6919
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3856 - loss: 1.6892
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3839 - loss: 1.6909
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3824 - loss: 1.6908
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6920
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3800 - loss: 1.6931
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3798 - loss: 1.6932
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3798 - loss: 1.6924
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3800 - loss: 1.6916
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3804 - loss: 1.6908
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6896
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3814 - loss: 1.6886
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3817 - loss: 1.6877
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3821 - loss: 1.6869
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3824 - loss: 1.6862
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3827 - loss: 1.6858
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3829 - loss: 1.6851
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3831 - loss: 1.6846
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6841
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6839
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6836
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6834
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6831
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6827
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6823
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6820
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6818
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6817
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6817
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6817
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6817
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6817
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6816
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6815
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6814
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6813
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6811
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6810
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6808
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6806
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6804
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6802
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6799
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6797
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6797 - val_accuracy: 0.3704 - val_loss: 1.7708
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.6173
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4263 - loss: 1.5566  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4257 - loss: 1.5771
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4220 - loss: 1.5907
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4161 - loss: 1.6076
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4128 - loss: 1.6150
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4109 - loss: 1.6185
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4090 - loss: 1.6218
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4075 - loss: 1.6246
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4065 - loss: 1.6267
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4054 - loss: 1.6286
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4044 - loss: 1.6303
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6319
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4027 - loss: 1.6332
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4020 - loss: 1.6340
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4016 - loss: 1.6345
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4013 - loss: 1.6347
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4010 - loss: 1.6349
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4008 - loss: 1.6352
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4006 - loss: 1.6353
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4003 - loss: 1.6357
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4001 - loss: 1.6360
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3999 - loss: 1.6364
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3997 - loss: 1.6368
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3995 - loss: 1.6372
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3993 - loss: 1.6376
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3992 - loss: 1.6381
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3990 - loss: 1.6386
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3989 - loss: 1.6390
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3987 - loss: 1.6395
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3985 - loss: 1.6400
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3984 - loss: 1.6406
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6410
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3980 - loss: 1.6415
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3979 - loss: 1.6419
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3977 - loss: 1.6424
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3975 - loss: 1.6427
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3974 - loss: 1.6430
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3973 - loss: 1.6432
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6436
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6438
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6441
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6444
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6447
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3965 - loss: 1.6450
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6452 - val_accuracy: 0.3628 - val_loss: 1.7826
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.6814
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4001 - loss: 1.5745  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3853 - loss: 1.5827
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3814 - loss: 1.5921
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3789 - loss: 1.5984
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3779 - loss: 1.6024
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6095
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3768 - loss: 1.6145
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3768 - loss: 1.6180
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3773 - loss: 1.6208
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3779 - loss: 1.6228
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3782 - loss: 1.6240
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.6255
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.6273
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.6293
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3788 - loss: 1.6310
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3789 - loss: 1.6325
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3788 - loss: 1.6341
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3789 - loss: 1.6356
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3789 - loss: 1.6370
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3790 - loss: 1.6380
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.6391
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3790 - loss: 1.6402
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3790 - loss: 1.6412
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.6418
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.6425
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3792 - loss: 1.6433
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3793 - loss: 1.6439
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6444
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3797 - loss: 1.6448
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3799 - loss: 1.6452
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3801 - loss: 1.6456
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3803 - loss: 1.6459
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3804 - loss: 1.6462
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3806 - loss: 1.6465
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3808 - loss: 1.6468
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6471
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3811 - loss: 1.6473
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3813 - loss: 1.6474
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3815 - loss: 1.6477
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3816 - loss: 1.6479
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6480
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3820 - loss: 1.6482
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6483
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3823 - loss: 1.6484
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3824 - loss: 1.6485 - val_accuracy: 0.3726 - val_loss: 1.7540

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:30[0m 1s/step
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:32:28.817331: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:22[0m 1s/step
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m108/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 941us/step
[1m158/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 963us/step
[1m216/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 939us/step
[1m267/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 948us/step
[1m320/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 949us/step
[1m378/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 938us/step
[1m435/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 932us/step
[1m494/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 923us/step
[1m551/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 919us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 967us/step
[1m111/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 918us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 38.28 [%]
Global F1 score (validation) = 35.97 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.1924937  0.24350686 0.16645727 ... 0.0023629  0.15217659 0.00991802]
 [0.22045158 0.23114146 0.19468412 ... 0.00416027 0.17513388 0.0101221 ]
 [0.22056103 0.19539203 0.21531832 ... 0.01095711 0.17145273 0.03090162]
 ...
 [0.21362856 0.23253211 0.18796499 ... 0.00475521 0.15043604 0.01335049]
 [0.22588599 0.22627257 0.21126842 ... 0.00089862 0.19494106 0.01193406]
 [0.18505959 0.21182032 0.15643904 ... 0.00872836 0.11953893 0.01106486]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 47.0 [%]
Global accuracy score (test) = 31.64 [%]
Global F1 score (train) = 44.87 [%]
Global F1 score (test) = 28.84 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.22      0.14      0.17       184
 CAMINAR CON MÓVIL O LIBRO       0.23      0.57      0.32       184
       CAMINAR USUAL SPEED       0.07      0.04      0.05       184
            CAMINAR ZIGZAG       0.55      0.45      0.50       184
          DE PIE BARRIENDO       0.33      0.46      0.38       184
   DE PIE DOBLANDO TOALLAS       0.12      0.01      0.01       184
    DE PIE MOVIENDO LIBROS       0.28      0.45      0.34       184
          DE PIE USANDO PC       0.30      0.66      0.42       184
        FASE REPOSO CON K5       0.98      0.52      0.68       184
INCREMENTAL CICLOERGOMETRO       0.61      0.53      0.57       184
           SENTADO LEYENDO       0.24      0.39      0.30       184
         SENTADO USANDO PC       0.20      0.10      0.13       184
      SENTADO VIENDO LA TV       0.00      0.00      0.00       184
   SUBIR Y BAJAR ESCALERAS       0.12      0.05      0.07       184
                    TROTAR       0.38      0.38      0.38       161

                  accuracy                           0.32      2737
                 macro avg       0.31      0.32      0.29      2737
              weighted avg       0.31      0.32      0.29      2737


Accuracy capturado en la ejecución 9: 31.64 [%]
F1-score capturado en la ejecución 9: 28.84 [%]

=== EJECUCIÓN 10 ===

--- TRAIN (ejecución 10) ---

--- TEST (ejecución 10) ---
2025-10-31 15:32:42.092789: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:32:42.104206: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761921162.117564 1673440 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761921162.121811 1673440 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761921162.131799 1673440 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921162.131822 1673440 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921162.131824 1673440 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921162.131825 1673440 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:32:42.135078: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761921164.523906 1673440 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761921167.613177 1673543 service.cc:152] XLA service 0x78a6c401b670 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761921167.613247 1673543 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:32:47.682900: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761921168.103358 1673543 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761921170.696864 1673543 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45:04[0m 5s/step - accuracy: 0.1250 - loss: 3.0588
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.0547 - loss: 3.3872    
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0550 - loss: 3.4065
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0576 - loss: 3.3969
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0603 - loss: 3.3765
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0621 - loss: 3.3594
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0633 - loss: 3.3435
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0645 - loss: 3.3282
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0657 - loss: 3.3143
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0670 - loss: 3.2995
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0684 - loss: 3.2854
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0698 - loss: 3.2720
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0711 - loss: 3.2590
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0723 - loss: 3.2465
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0736 - loss: 3.2350
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0749 - loss: 3.2226
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0761 - loss: 3.2117
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0772 - loss: 3.2013
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0783 - loss: 3.1909
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0795 - loss: 3.1806
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0807 - loss: 3.1701
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0817 - loss: 3.1612
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0828 - loss: 3.1517
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0838 - loss: 3.1423
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0849 - loss: 3.1326
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0858 - loss: 3.1252
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0868 - loss: 3.1167
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0876 - loss: 3.1093
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0885 - loss: 3.1015
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0894 - loss: 3.0942
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0902 - loss: 3.0874
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0910 - loss: 3.0799
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0917 - loss: 3.0740
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0925 - loss: 3.0674
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0933 - loss: 3.0610
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0941 - loss: 3.0538
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0948 - loss: 3.0480
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0955 - loss: 3.0414
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0962 - loss: 3.0352
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0968 - loss: 3.0298
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0975 - loss: 3.0238
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0982 - loss: 3.0176
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0989 - loss: 3.0122
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0995 - loss: 3.0063
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.0998 - loss: 3.0041
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.0998 - loss: 3.0039 - val_accuracy: 0.1911 - val_loss: 2.3016
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.5571
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1699 - loss: 2.5232  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1725 - loss: 2.4852
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1752 - loss: 2.4719
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1770 - loss: 2.4644
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1770 - loss: 2.4603
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.4575
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.4556
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.4542
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1768 - loss: 2.4528
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1761 - loss: 2.4535
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1753 - loss: 2.4542
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1745 - loss: 2.4552
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1738 - loss: 2.4562
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1732 - loss: 2.4572
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1726 - loss: 2.4579
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1722 - loss: 2.4580
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1718 - loss: 2.4580
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1715 - loss: 2.4578
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.4577
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1708 - loss: 2.4575
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1704 - loss: 2.4573
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1701 - loss: 2.4569
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1699 - loss: 2.4565
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1697 - loss: 2.4559
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1695 - loss: 2.4553
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1693 - loss: 2.4548
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1691 - loss: 2.4542
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1689 - loss: 2.4538
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1687 - loss: 2.4532
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1685 - loss: 2.4527
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1683 - loss: 2.4521
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1682 - loss: 2.4516
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1680 - loss: 2.4509
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1679 - loss: 2.4502
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1678 - loss: 2.4495
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1677 - loss: 2.4487
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1676 - loss: 2.4480
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1675 - loss: 2.4473
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1674 - loss: 2.4465
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1673 - loss: 2.4457
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1672 - loss: 2.4449
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1671 - loss: 2.4442
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1671 - loss: 2.4436
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1670 - loss: 2.4431 - val_accuracy: 0.2006 - val_loss: 2.1938
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1250 - loss: 2.5217
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1704 - loss: 2.2997  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2957
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1799 - loss: 2.2927
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1798 - loss: 2.2984
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1792 - loss: 2.3054
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.3100
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.3126
[1m 223/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1768 - loss: 2.3145
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1764 - loss: 2.3158
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1764 - loss: 2.3169
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1765 - loss: 2.3181
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1766 - loss: 2.3193
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1766 - loss: 2.3206
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1766 - loss: 2.3215
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1767 - loss: 2.3220
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1767 - loss: 2.3222
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1769 - loss: 2.3221
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.3219
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1772 - loss: 2.3217
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1773 - loss: 2.3215
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1773 - loss: 2.3213
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.3209
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1775 - loss: 2.3205
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1776 - loss: 2.3201
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1777 - loss: 2.3197
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1778 - loss: 2.3192
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1778 - loss: 2.3188
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1779 - loss: 2.3183
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.3178
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.3173
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.3168
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1781 - loss: 2.3162
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1781 - loss: 2.3158
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1782 - loss: 2.3154
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1782 - loss: 2.3150
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1782 - loss: 2.3146
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1782 - loss: 2.3142
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1783 - loss: 2.3139
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1783 - loss: 2.3135
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1783 - loss: 2.3132
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1784 - loss: 2.3129
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1784 - loss: 2.3125
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1785 - loss: 2.3123 - val_accuracy: 0.2076 - val_loss: 2.1274
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 1.9428
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1582 - loss: 2.2309  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1642 - loss: 2.2593
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1693 - loss: 2.2646
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1709 - loss: 2.2665
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1713 - loss: 2.2667
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1721 - loss: 2.2659
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1730 - loss: 2.2645
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1741 - loss: 2.2629
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1750 - loss: 2.2611
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2594
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1765 - loss: 2.2582
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1769 - loss: 2.2575
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.2569
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.2562
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.2554
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1782 - loss: 2.2546
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1783 - loss: 2.2541
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1785 - loss: 2.2536
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1786 - loss: 2.2529
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1788 - loss: 2.2522
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1790 - loss: 2.2516
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1791 - loss: 2.2509
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1792 - loss: 2.2502
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1793 - loss: 2.2496
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.2491
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.2486
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.2481
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1800 - loss: 2.2476
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.2471
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.2467
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1806 - loss: 2.2463
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1808 - loss: 2.2459
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1810 - loss: 2.2455
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1812 - loss: 2.2451
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1814 - loss: 2.2448
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1816 - loss: 2.2444
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1818 - loss: 2.2440
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1821 - loss: 2.2436
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1822 - loss: 2.2433
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1825 - loss: 2.2429
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1827 - loss: 2.2425
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1830 - loss: 2.2420
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.2415
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2411
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2409 - val_accuracy: 0.2241 - val_loss: 2.0558
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.5611
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2011 - loss: 2.3241  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2111 - loss: 2.2588
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2149 - loss: 2.2340
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2151 - loss: 2.2206
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2146 - loss: 2.2112
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2142 - loss: 2.2051
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2138 - loss: 2.1996
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2134 - loss: 2.1949
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2131 - loss: 2.1916
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2128 - loss: 2.1890
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2125 - loss: 2.1870
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2122 - loss: 2.1856
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2120 - loss: 2.1842
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2118 - loss: 2.1828
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2116 - loss: 2.1814
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2114 - loss: 2.1799
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1788
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2111 - loss: 2.1776
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2110 - loss: 2.1767
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1757
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1749
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1741
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1734
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2108 - loss: 2.1729
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2108 - loss: 2.1725
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1720
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1717
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.1713
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2111 - loss: 2.1710
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1707
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2113 - loss: 2.1704
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2114 - loss: 2.1701
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2115 - loss: 2.1698
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2116 - loss: 2.1695
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2117 - loss: 2.1693
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2118 - loss: 2.1691
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2119 - loss: 2.1688
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2121 - loss: 2.1685
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2122 - loss: 2.1683
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2124 - loss: 2.1680
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2125 - loss: 2.1678
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2127 - loss: 2.1675
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2128 - loss: 2.1672
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.1670
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2131 - loss: 2.1669 - val_accuracy: 0.2492 - val_loss: 2.0310
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.0072
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2488 - loss: 2.0044  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2487 - loss: 2.0333
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2471 - loss: 2.0567
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2455 - loss: 2.0681
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2440 - loss: 2.0747
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.0783
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2416 - loss: 2.0829
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2406 - loss: 2.0870
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2398 - loss: 2.0905
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2390 - loss: 2.0937
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2386 - loss: 2.0964
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.0983
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.1002
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1018
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2369 - loss: 2.1028
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2366 - loss: 2.1038
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2363 - loss: 2.1045
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2361 - loss: 2.1051
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.1056
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.1059
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.1062
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2361 - loss: 2.1063
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2362 - loss: 2.1065
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2363 - loss: 2.1067
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2364 - loss: 2.1069
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2364 - loss: 2.1071
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2365 - loss: 2.1071
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2365 - loss: 2.1072
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2366 - loss: 2.1074
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2366 - loss: 2.1075
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2366 - loss: 2.1076
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2367 - loss: 2.1076
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2367 - loss: 2.1076
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2368 - loss: 2.1076
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2369 - loss: 2.1076
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2369 - loss: 2.1076
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2370 - loss: 2.1076
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2370 - loss: 2.1076
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1076
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1075
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1074
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1073
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1072
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2374 - loss: 2.1072 - val_accuracy: 0.2435 - val_loss: 1.9866
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3535
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2671 - loss: 2.0993  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2617 - loss: 2.1046
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2582 - loss: 2.1004
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2590 - loss: 2.0943
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.0897
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2605 - loss: 2.0864
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2610 - loss: 2.0840
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2617 - loss: 2.0812
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2623 - loss: 2.0791
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2626 - loss: 2.0772
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2628 - loss: 2.0756
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0744
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0735
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0726
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0721
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0717
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0715
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0712
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0709
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0706
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0706
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0706
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0705
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0704
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0702
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0699
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0696
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0692
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0689
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0686
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0683
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2632 - loss: 2.0680
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2632 - loss: 2.0677
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2632 - loss: 2.0674
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0671
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0667
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0663
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0660
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0656
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0653
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0649
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0646
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0643
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0642 - val_accuracy: 0.3539 - val_loss: 1.8670
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 1.8735
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2491 - loss: 1.9885  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2593 - loss: 1.9935
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2643 - loss: 1.9939
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2672 - loss: 1.9933
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2695 - loss: 1.9957
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2721 - loss: 1.9966
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2739 - loss: 1.9970
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2750 - loss: 1.9972
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2753 - loss: 1.9978
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2754 - loss: 1.9984
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2753 - loss: 1.9991
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2753 - loss: 1.9994
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2753 - loss: 1.9993
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2754 - loss: 1.9987
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2755 - loss: 1.9981
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2757 - loss: 1.9973
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2760 - loss: 1.9965
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2763 - loss: 1.9957
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 1.9949
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 1.9941
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2771 - loss: 1.9934
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2775 - loss: 1.9928
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 1.9924
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2781 - loss: 1.9920
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2785 - loss: 1.9916
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2788 - loss: 1.9913
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2791 - loss: 1.9911
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2794 - loss: 1.9908
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 1.9907
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 1.9905
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9902
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 1.9899
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2804 - loss: 1.9897
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2806 - loss: 1.9895
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 1.9894
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 1.9893
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2810 - loss: 1.9891
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 1.9890
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2813 - loss: 1.9888
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9887
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2815 - loss: 1.9886
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 1.9884
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 1.9883
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 1.9882
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2819 - loss: 1.9882 - val_accuracy: 0.3186 - val_loss: 1.8635
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.9783
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3249 - loss: 1.9641  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3195 - loss: 1.9712
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3159 - loss: 1.9785
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3153 - loss: 1.9787
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 1.9774
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 1.9745
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 1.9718
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 1.9706
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 1.9697
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 1.9686
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 1.9673
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3088 - loss: 1.9663
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3086 - loss: 1.9659
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 1.9655
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 1.9652
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3081 - loss: 1.9649
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 1.9647
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3079 - loss: 1.9642
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 1.9639
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3076 - loss: 1.9637
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 1.9635
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3073 - loss: 1.9633
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 1.9632
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 1.9632
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 1.9631
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 1.9630
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 1.9630
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9629
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.9628
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 1.9627
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9626
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9624
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9623
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9621
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9619
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9616
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9613
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9611
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9609
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9606
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9605
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9603
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9601
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9600 - val_accuracy: 0.3443 - val_loss: 1.8179
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9930
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3094 - loss: 1.9326  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9495
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3045 - loss: 1.9476
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3050 - loss: 1.9412
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9358
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9323
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 1.9286
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 1.9250
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 1.9209
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 1.9169
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 1.9138
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 1.9112
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 1.9091
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 1.9068
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 1.9047
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 1.9028
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 1.9013
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 1.9002
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3154 - loss: 1.8994
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 1.8989
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 1.8984
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3159 - loss: 1.8980
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3161 - loss: 1.8978
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3162 - loss: 1.8975
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3164 - loss: 1.8973
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8971
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8968
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8966
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 1.8963
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8961
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8959
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 1.8956
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8954
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8953
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8952
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8951
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 1.8950
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8949
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8948
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8947
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3184 - loss: 1.8945
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8944
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8943 - val_accuracy: 0.3425 - val_loss: 1.8376
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.3750 - loss: 1.6404
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2866 - loss: 1.9002  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2982 - loss: 1.9008
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3044 - loss: 1.8981
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3087 - loss: 1.8961
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8945
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 1.8946
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 1.8937
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 1.8938
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 1.8942
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 1.8942
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 1.8943
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 1.8942
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8940
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8941
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8943
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8943
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3181 - loss: 1.8942
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8940
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8937
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8935
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8932
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8929
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 1.8925
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3209 - loss: 1.8921
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3213 - loss: 1.8916
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3217 - loss: 1.8912
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 1.8908
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 1.8903
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.8897
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 1.8892
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 1.8888
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 1.8883
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 1.8879
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 1.8875
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 1.8871
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8868
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8865
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3243 - loss: 1.8862
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8859
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8856
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3245 - loss: 1.8853
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8850
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8847
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8846 - val_accuracy: 0.3554 - val_loss: 1.7873
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.9500
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3352 - loss: 1.9398  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3441 - loss: 1.8907
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3445 - loss: 1.8706
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3474 - loss: 1.8527
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8432
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3489 - loss: 1.8369
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8324
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3483 - loss: 1.8308
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3482 - loss: 1.8300
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8291
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3489 - loss: 1.8284
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3494 - loss: 1.8276
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3497 - loss: 1.8266
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3499 - loss: 1.8258
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3501 - loss: 1.8251
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3502 - loss: 1.8245
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3502 - loss: 1.8240
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3502 - loss: 1.8233
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3501 - loss: 1.8230
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.8227
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.8225
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3498 - loss: 1.8224
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3497 - loss: 1.8224
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.8223
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3494 - loss: 1.8223
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.8223
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3490 - loss: 1.8223
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3489 - loss: 1.8225
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8226
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3484 - loss: 1.8227
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3483 - loss: 1.8228
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3481 - loss: 1.8229
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3479 - loss: 1.8231
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3477 - loss: 1.8232
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3476 - loss: 1.8233
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3475 - loss: 1.8234
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3473 - loss: 1.8234
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.8235
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.8236
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3470 - loss: 1.8236
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3469 - loss: 1.8237
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3468 - loss: 1.8238
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3467 - loss: 1.8239
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3467 - loss: 1.8239 - val_accuracy: 0.3510 - val_loss: 1.8018
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.1250 - loss: 1.9455
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.3379 - loss: 1.7664  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3490 - loss: 1.8026
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8155
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3487 - loss: 1.8195
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8175
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8158
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.8147
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3490 - loss: 1.8148
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.8160
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3482 - loss: 1.8170
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3479 - loss: 1.8179
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3479 - loss: 1.8182
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3478 - loss: 1.8181
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3480 - loss: 1.8176
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3482 - loss: 1.8167
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3484 - loss: 1.8160
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3484 - loss: 1.8156
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.8154
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8151
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3487 - loss: 1.8146
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8140
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3489 - loss: 1.8135
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8129
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.8124
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3493 - loss: 1.8120
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3494 - loss: 1.8116
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3494 - loss: 1.8114
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.8112
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3494 - loss: 1.8111
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.8110
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.8108
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.8106
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.8104
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3497 - loss: 1.8100
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3498 - loss: 1.8098
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.8096
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.8095
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3500 - loss: 1.8093
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3501 - loss: 1.8092
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3501 - loss: 1.8091
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3501 - loss: 1.8090
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3502 - loss: 1.8089
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3502 - loss: 1.8088
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3502 - loss: 1.8087 - val_accuracy: 0.3460 - val_loss: 1.8107
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.5890
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3922 - loss: 1.7780  
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3795 - loss: 1.7603
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7563
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3738 - loss: 1.7534
[1m 140/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7539
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7553
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7580
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7614
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3617 - loss: 1.7631
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7648
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7663
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7678
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7688
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7695
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7703
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7710
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7719
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7727
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3541 - loss: 1.7735
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7740
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7747
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7754
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7760
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7764
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7767
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7768
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7770
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7772
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7776
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7779
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7782
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7785
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7786
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7788
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7790
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7791
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7792
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7793
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7793
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7794
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7795
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7797
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7798
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7799
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7799 - val_accuracy: 0.3743 - val_loss: 1.7787
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7126
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7327  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3516 - loss: 1.7270
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3504 - loss: 1.7301
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7375
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3478 - loss: 1.7425
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3487 - loss: 1.7441
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3501 - loss: 1.7454
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7464
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7487
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3522 - loss: 1.7508
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3530 - loss: 1.7519
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7527
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3541 - loss: 1.7532
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7532
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7529
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7526
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7523
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7521
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7519
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7519
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7522
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7525
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7528
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7530
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7534
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7538
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7542
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7547
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7552
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7556
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7560
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7563
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7567
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7571
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7574
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7578
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7581
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7584
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7586
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7588
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7590
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7592
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7593 - val_accuracy: 0.3630 - val_loss: 1.8086
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.7886
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3749 - loss: 1.6894  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3829 - loss: 1.6777
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3783 - loss: 1.6876
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6920
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.6939
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.6951
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3782 - loss: 1.6969
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.6992
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.7012
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.7025
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.7032
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.7035
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.7040
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.7047
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3779 - loss: 1.7053
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7060
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7068
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7077
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3762 - loss: 1.7087
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3757 - loss: 1.7097
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3754 - loss: 1.7105
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7115
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3748 - loss: 1.7123
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3746 - loss: 1.7130
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3745 - loss: 1.7136
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7141
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7145
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3738 - loss: 1.7150
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3736 - loss: 1.7155
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7161
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7166
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7170
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3730 - loss: 1.7174
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7178
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7182
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7185
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7188
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7190
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3726 - loss: 1.7193
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7195
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7197
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7199
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7202
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7202 - val_accuracy: 0.3545 - val_loss: 1.7952
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.3744
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4107 - loss: 1.6402  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3893 - loss: 1.6898
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3822 - loss: 1.7100
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3757 - loss: 1.7290
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7330
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7327
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7332
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7325
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7321
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7328
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7329
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7326
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7321
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7316
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7309
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7303
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7299
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7296
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7294
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7293
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7290
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7286
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7280
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7276
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7273
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7269
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7266
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7262
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3726 - loss: 1.7258
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7255
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7252
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7249
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3730 - loss: 1.7246
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3730 - loss: 1.7243
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7239
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7236
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3732 - loss: 1.7233
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3732 - loss: 1.7230
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7227
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7225
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7223
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7221
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7220
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7219 - val_accuracy: 0.3676 - val_loss: 1.7991
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.2500 - loss: 1.9359
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3548 - loss: 1.6712  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3640 - loss: 1.6647
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3686 - loss: 1.6622
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3724 - loss: 1.6587
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3756 - loss: 1.6578
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3776 - loss: 1.6590
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3788 - loss: 1.6625
[1m 223/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3797 - loss: 1.6653
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6663
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6665
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6671
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3836 - loss: 1.6679
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6686
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6691
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6701
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3851 - loss: 1.6710
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3852 - loss: 1.6721
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3853 - loss: 1.6732
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3853 - loss: 1.6744
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3853 - loss: 1.6753
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3852 - loss: 1.6762
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3852 - loss: 1.6772
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3850 - loss: 1.6781
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6788
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6794
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3848 - loss: 1.6799
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6804
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6809
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6814
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6818
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6821
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6824
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6828
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6831
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6834
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6837
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6840
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6843
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6847
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6849
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6852
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6855
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6858
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6858 - val_accuracy: 0.3724 - val_loss: 1.8169
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.3125 - loss: 2.0053
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3549 - loss: 1.8240  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7800
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3809 - loss: 1.7600
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3848 - loss: 1.7458
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3861 - loss: 1.7381
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3859 - loss: 1.7324
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3862 - loss: 1.7276
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3869 - loss: 1.7240
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3869 - loss: 1.7223
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3866 - loss: 1.7216
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3866 - loss: 1.7208
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3863 - loss: 1.7201
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3859 - loss: 1.7196
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3856 - loss: 1.7190
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3855 - loss: 1.7184
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3855 - loss: 1.7178
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3854 - loss: 1.7173
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3853 - loss: 1.7168
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3852 - loss: 1.7165
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3851 - loss: 1.7161
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3850 - loss: 1.7156
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3850 - loss: 1.7150
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3850 - loss: 1.7143
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3851 - loss: 1.7134
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3852 - loss: 1.7125
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3853 - loss: 1.7118
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.7110
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.7104
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.7097
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.7091
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.7086
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3853 - loss: 1.7082
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3853 - loss: 1.7079
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3852 - loss: 1.7074
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3852 - loss: 1.7071
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3851 - loss: 1.7067
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3851 - loss: 1.7063
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3852 - loss: 1.7058
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3852 - loss: 1.7053
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3853 - loss: 1.7048
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3853 - loss: 1.7043
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.7038
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.7034
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3854 - loss: 1.7033 - val_accuracy: 0.3563 - val_loss: 1.8431

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:33[0m 1s/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:33:48.586241: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:23[0m 1s/step
[1m 43/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m 89/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m138/584[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m191/584[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m243/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m296/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m340/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m392/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step
[1m446/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 1ms/step
[1m505/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1000us/step
[1m562/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 989us/step 
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 49/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m101/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m158/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 962us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 37.26 [%]
Global F1 score (validation) = 34.43 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.2216067  0.22840093 0.24375524 ... 0.00185283 0.18886219 0.02677785]
 [0.2051452  0.22114004 0.17925319 ... 0.00171047 0.19824629 0.01294293]
 [0.22274819 0.27226636 0.2248395  ... 0.00143554 0.1559406  0.00868409]
 ...
 [0.19765939 0.24753645 0.18037644 ... 0.00453206 0.14709044 0.00908015]
 [0.220763   0.22487432 0.22900742 ... 0.00135014 0.20207858 0.01934185]
 [0.20588487 0.2503041  0.18538962 ... 0.00273978 0.14300752 0.00752268]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.82 [%]
Global accuracy score (test) = 30.95 [%]
Global F1 score (train) = 43.85 [%]
Global F1 score (test) = 29.03 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.22      0.03      0.05       184
 CAMINAR CON MÓVIL O LIBRO       0.20      0.46      0.28       184
       CAMINAR USUAL SPEED       0.15      0.10      0.12       184
            CAMINAR ZIGZAG       0.48      0.50      0.49       184
          DE PIE BARRIENDO       0.30      0.38      0.33       184
   DE PIE DOBLANDO TOALLAS       0.41      0.08      0.13       184
    DE PIE MOVIENDO LIBROS       0.29      0.57      0.38       184
          DE PIE USANDO PC       0.25      0.67      0.36       184
        FASE REPOSO CON K5       0.99      0.38      0.55       184
INCREMENTAL CICLOERGOMETRO       0.77      0.57      0.66       184
           SENTADO LEYENDO       0.22      0.23      0.23       184
         SENTADO USANDO PC       0.12      0.06      0.08       184
      SENTADO VIENDO LA TV       0.61      0.11      0.18       184
   SUBIR Y BAJAR ESCALERAS       0.18      0.15      0.16       184
                    TROTAR       0.34      0.37      0.35       161

                  accuracy                           0.31      2737
                 macro avg       0.37      0.31      0.29      2737
              weighted avg       0.37      0.31      0.29      2737


Accuracy capturado en la ejecución 10: 30.95 [%]
F1-score capturado en la ejecución 10: 29.03 [%]

=== EJECUCIÓN 11 ===

--- TRAIN (ejecución 11) ---

--- TEST (ejecución 11) ---
2025-10-31 15:34:01.852809: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:34:01.864048: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761921241.877315 1676665 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761921241.881520 1676665 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761921241.891354 1676665 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921241.891375 1676665 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921241.891377 1676665 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921241.891379 1676665 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:34:01.894560: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761921244.263412 1676665 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761921247.410532 1676756 service.cc:152] XLA service 0x7212d401b230 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761921247.410571 1676756 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:34:07.474032: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761921247.895257 1676756 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761921250.530873 1676756 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:01[0m 6s/step - accuracy: 0.0000e+00 - loss: 3.5722
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.0496 - loss: 3.5961        
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0520 - loss: 3.5139
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0567 - loss: 3.4510
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0590 - loss: 3.4078
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0611 - loss: 3.3754
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0632 - loss: 3.3495
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0651 - loss: 3.3285
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0666 - loss: 3.3128
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0680 - loss: 3.2984
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0692 - loss: 3.2832
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0706 - loss: 3.2683
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0719 - loss: 3.2551
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0731 - loss: 3.2439
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0742 - loss: 3.2318
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0752 - loss: 3.2212
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0763 - loss: 3.2103
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0773 - loss: 3.2006
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0783 - loss: 3.1911
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0793 - loss: 3.1820
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0803 - loss: 3.1733
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0812 - loss: 3.1649
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0822 - loss: 3.1560
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0830 - loss: 3.1484
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0839 - loss: 3.1406
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0848 - loss: 3.1328
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0856 - loss: 3.1255
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0864 - loss: 3.1182
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0872 - loss: 3.1111
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0879 - loss: 3.1045
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0885 - loss: 3.0983
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0892 - loss: 3.0918
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0899 - loss: 3.0854
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0906 - loss: 3.0790
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0912 - loss: 3.0728
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0919 - loss: 3.0670
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0925 - loss: 3.0612
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0930 - loss: 3.0557
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0935 - loss: 3.0504
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0940 - loss: 3.0451
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0946 - loss: 3.0397
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0951 - loss: 3.0343
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0956 - loss: 3.0290
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0961 - loss: 3.0241
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0965 - loss: 3.0195
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.0968 - loss: 3.0162
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.0968 - loss: 3.0160 - val_accuracy: 0.1604 - val_loss: 2.3522
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.6043
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1643 - loss: 2.5493  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1563 - loss: 2.5364
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1545 - loss: 2.5314
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1548 - loss: 2.5303
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1543 - loss: 2.5295
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1542 - loss: 2.5272
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1538 - loss: 2.5252
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1531 - loss: 2.5240
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1528 - loss: 2.5232
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1525 - loss: 2.5226
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1522 - loss: 2.5217
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1520 - loss: 2.5207
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1518 - loss: 2.5199
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1518 - loss: 2.5189
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1520 - loss: 2.5180
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1523 - loss: 2.5169
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1526 - loss: 2.5157
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1528 - loss: 2.5146
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1529 - loss: 2.5135
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1531 - loss: 2.5123
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1532 - loss: 2.5110
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1533 - loss: 2.5099
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1534 - loss: 2.5086
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1536 - loss: 2.5073
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1537 - loss: 2.5062
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1539 - loss: 2.5050
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1540 - loss: 2.5038
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1542 - loss: 2.5027
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1543 - loss: 2.5018
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1545 - loss: 2.5008
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1546 - loss: 2.4997
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1548 - loss: 2.4986
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1549 - loss: 2.4976
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1551 - loss: 2.4964
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1552 - loss: 2.4954
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1553 - loss: 2.4943
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4933
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4924
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4914
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4904
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4895
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1556 - loss: 2.4884
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1556 - loss: 2.4875
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1557 - loss: 2.4865
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1557 - loss: 2.4857 - val_accuracy: 0.1769 - val_loss: 2.2167
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.4433
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1618 - loss: 2.3896  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1629 - loss: 2.3948
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1629 - loss: 2.3992
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1638 - loss: 2.4015
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1643 - loss: 2.4009
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1643 - loss: 2.4002
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1641 - loss: 2.3997
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1644 - loss: 2.3981
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1649 - loss: 2.3965
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3947
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1657 - loss: 2.3931
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1663 - loss: 2.3911
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3889
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1669 - loss: 2.3873
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1671 - loss: 2.3859
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1674 - loss: 2.3843
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1677 - loss: 2.3827
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3811
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1682 - loss: 2.3798
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3785
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1687 - loss: 2.3771
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1690 - loss: 2.3757
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3742
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1695 - loss: 2.3729
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1697 - loss: 2.3715
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1700 - loss: 2.3703
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1701 - loss: 2.3693
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1702 - loss: 2.3684
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1704 - loss: 2.3673
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1705 - loss: 2.3663
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1706 - loss: 2.3653
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1707 - loss: 2.3643
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1708 - loss: 2.3634
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3624
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1710 - loss: 2.3615
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1710 - loss: 2.3607
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3597
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1713 - loss: 2.3588
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3580
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3572
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1716 - loss: 2.3564
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1717 - loss: 2.3556
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3549
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1719 - loss: 2.3542
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1720 - loss: 2.3536
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1720 - loss: 2.3532 - val_accuracy: 0.2000 - val_loss: 2.1425
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.0625 - loss: 2.2219
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1520 - loss: 2.2173  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1651 - loss: 2.2385
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1695 - loss: 2.2444
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1719 - loss: 2.2500
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1733 - loss: 2.2526
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1751 - loss: 2.2536
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1770 - loss: 2.2522
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1785 - loss: 2.2508
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1797 - loss: 2.2499
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1805 - loss: 2.2491
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1812 - loss: 2.2482
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.2479
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1820 - loss: 2.2481
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2485
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.2490
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.2494
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1831 - loss: 2.2500
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1833 - loss: 2.2506
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2511
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2516
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2519
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1842 - loss: 2.2521
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1844 - loss: 2.2522
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2523
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2524
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2524
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2523
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1851 - loss: 2.2523
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2521
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2520
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2518
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2516
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2515
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2513
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2511
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2510
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2509
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2508
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2506
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2505
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2503
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2502
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2500
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2498
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2496
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2495 - val_accuracy: 0.2265 - val_loss: 2.0702
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3519
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1928 - loss: 2.3030  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1995 - loss: 2.2770
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2610
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2017 - loss: 2.2516
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2017 - loss: 2.2460
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2007 - loss: 2.2438
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2000 - loss: 2.2410
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1997 - loss: 2.2387
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1996 - loss: 2.2368
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1996 - loss: 2.2353
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1998 - loss: 2.2336
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2001 - loss: 2.2321
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2002 - loss: 2.2312
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2001 - loss: 2.2307
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2000 - loss: 2.2300
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2000 - loss: 2.2293
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1999 - loss: 2.2283
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1999 - loss: 2.2275
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2000 - loss: 2.2267
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2001 - loss: 2.2258
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2002 - loss: 2.2248
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2003 - loss: 2.2239
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2003 - loss: 2.2232
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2004 - loss: 2.2225
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2004 - loss: 2.2218
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2005 - loss: 2.2210
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2005 - loss: 2.2203
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2005 - loss: 2.2197
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2005 - loss: 2.2191
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2005 - loss: 2.2185
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2006 - loss: 2.2180
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2006 - loss: 2.2174
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2007 - loss: 2.2168
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2007 - loss: 2.2162
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2008 - loss: 2.2156
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2151
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.2144
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.2137
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2012 - loss: 2.2132
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2013 - loss: 2.2126
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2014 - loss: 2.2120
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2014 - loss: 2.2114
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2015 - loss: 2.2109
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2016 - loss: 2.2104
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2016 - loss: 2.2101 - val_accuracy: 0.2496 - val_loss: 2.0229
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1875 - loss: 2.1476
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1856 - loss: 2.1433  
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1932 - loss: 2.1444
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1973 - loss: 2.1437
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1997 - loss: 2.1412
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2018 - loss: 2.1402
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2040 - loss: 2.1389
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2057 - loss: 2.1373
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2067 - loss: 2.1363
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2073 - loss: 2.1357
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2079 - loss: 2.1353
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2085 - loss: 2.1348
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2092 - loss: 2.1344
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2097 - loss: 2.1343
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2100 - loss: 2.1345
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2101 - loss: 2.1350
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2102 - loss: 2.1356
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2102 - loss: 2.1361
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2103 - loss: 2.1365
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2104 - loss: 2.1369
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2107 - loss: 2.1371
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2108 - loss: 2.1371
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2111 - loss: 2.1371
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2113 - loss: 2.1370
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2114 - loss: 2.1369
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2115 - loss: 2.1369
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2116 - loss: 2.1370
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2117 - loss: 2.1370
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2117 - loss: 2.1371
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2118 - loss: 2.1371
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2120 - loss: 2.1371
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2121 - loss: 2.1370
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2123 - loss: 2.1369
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2124 - loss: 2.1368
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2125 - loss: 2.1367
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2126 - loss: 2.1366
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2128 - loss: 2.1365
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.1365
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.1364
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.1363
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2133 - loss: 2.1362
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2135 - loss: 2.1361
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2136 - loss: 2.1359
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2138 - loss: 2.1358
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2139 - loss: 2.1357
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2140 - loss: 2.1355
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2140 - loss: 2.1355 - val_accuracy: 0.2638 - val_loss: 1.9875
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2500 - loss: 2.1160
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2393 - loss: 2.2006  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2370 - loss: 2.1792
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2351 - loss: 2.1626
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2351 - loss: 2.1524
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2347 - loss: 2.1445
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2340 - loss: 2.1402
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2332 - loss: 2.1370
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2324 - loss: 2.1349
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2319 - loss: 2.1335
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2315 - loss: 2.1324
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2311 - loss: 2.1315
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2310 - loss: 2.1304
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2309 - loss: 2.1292
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2308 - loss: 2.1282
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2307 - loss: 2.1276
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2306 - loss: 2.1266
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2306 - loss: 2.1256
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2307 - loss: 2.1245
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2309 - loss: 2.1236
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2311 - loss: 2.1226
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2314 - loss: 2.1214
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2318 - loss: 2.1202
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2321 - loss: 2.1189
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2324 - loss: 2.1177
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2328 - loss: 2.1165
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2331 - loss: 2.1153
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.1140
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.1128
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.1118
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2346 - loss: 2.1108
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2349 - loss: 2.1099
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2353 - loss: 2.1090
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.1081
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2359 - loss: 2.1073
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2362 - loss: 2.1064
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2365 - loss: 2.1057
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2368 - loss: 2.1050
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1042
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1036
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2375 - loss: 2.1030
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2378 - loss: 2.1023
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2380 - loss: 2.1017
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2383 - loss: 2.1010
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2385 - loss: 2.1004
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2388 - loss: 2.0997
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2389 - loss: 2.0995 - val_accuracy: 0.3095 - val_loss: 1.9306
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2662
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1661  
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2740 - loss: 2.1630
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2724 - loss: 2.1425
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2742 - loss: 2.1204
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2755 - loss: 2.1051
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2759 - loss: 2.0941
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2755 - loss: 2.0875
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2747 - loss: 2.0831
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2739 - loss: 2.0778
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2736 - loss: 2.0738
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2733 - loss: 2.0704
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2729 - loss: 2.0674
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2727 - loss: 2.0644
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0616
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0589
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0562
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0543
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.0525
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2724 - loss: 2.0511
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2723 - loss: 2.0498
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0487
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2721 - loss: 2.0474
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0463
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0454
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2718 - loss: 2.0447
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0441
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0437
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2714 - loss: 2.0434
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0429
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2712 - loss: 2.0425
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0422
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.0419
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0416
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.0414
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2704 - loss: 2.0410
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.0406
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.0403
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.0399
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.0395
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.0391
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.0388
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.0384
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.0380
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2696 - loss: 2.0377
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2696 - loss: 2.0374
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2696 - loss: 2.0373 - val_accuracy: 0.2971 - val_loss: 1.9373
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1875 - loss: 2.0398
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2254 - loss: 2.0610  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2312 - loss: 2.0558
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2391 - loss: 2.0439
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2459 - loss: 2.0341
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2517 - loss: 2.0250
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2563 - loss: 2.0169
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.0109
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2624 - loss: 2.0084
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2645 - loss: 2.0066
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0049
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.0034
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2684 - loss: 2.0016
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2694 - loss: 2.0001
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 1.9991
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 1.9980
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2717 - loss: 1.9969
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2722 - loss: 1.9960
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 1.9952
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2729 - loss: 1.9946
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2732 - loss: 1.9942
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 1.9939
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2736 - loss: 1.9938
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2739 - loss: 1.9937
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2740 - loss: 1.9936
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2742 - loss: 1.9935
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2744 - loss: 1.9934
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2746 - loss: 1.9932
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2748 - loss: 1.9929
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2751 - loss: 1.9927
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2752 - loss: 1.9925
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2754 - loss: 1.9923
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2755 - loss: 1.9921
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2756 - loss: 1.9920
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2758 - loss: 1.9918
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2759 - loss: 1.9916
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2761 - loss: 1.9914
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2763 - loss: 1.9912
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2764 - loss: 1.9910
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2765 - loss: 1.9907
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 1.9905
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2768 - loss: 1.9902
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 1.9900
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 1.9899
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 1.9897
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2774 - loss: 1.9896 - val_accuracy: 0.3042 - val_loss: 1.9313
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 1.6860
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3149 - loss: 1.9309  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3047 - loss: 1.9560
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3049 - loss: 1.9552
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9539
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 1.9547
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 1.9525
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9507
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 1.9496
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 1.9486
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9472
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2978 - loss: 1.9457
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 1.9441
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9430
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9419
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9407
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9397
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9389
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9384
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9379
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9375
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9371
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9367
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9363
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9359
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9357
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9356
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9354
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9353
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9353
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9353
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9353
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9354
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9354
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9355
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9356
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9357
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9357
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9357
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9357
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9357
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9358
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9358
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9359
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9359 - val_accuracy: 0.3488 - val_loss: 1.8116
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.6881
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3151 - loss: 1.8713  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3126 - loss: 1.8645
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3121 - loss: 1.8619
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3123 - loss: 1.8627
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3130 - loss: 1.8655
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3136 - loss: 1.8681
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 1.8711
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 1.8741
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 1.8771
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 1.8793
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 1.8813
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 1.8827
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3121 - loss: 1.8834
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8841
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8849
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8856
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8860
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 1.8864
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8866
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8867
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 1.8867
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 1.8867
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 1.8868
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 1.8866
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 1.8866
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8866
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8866
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8866
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 1.8866
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 1.8867
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 1.8868
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8869
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8869
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8869
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8870
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 1.8870
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 1.8871
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 1.8872
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 1.8874
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 1.8875
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 1.8876
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 1.8877
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8877
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8878
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8878 - val_accuracy: 0.3456 - val_loss: 1.8107
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.7858
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3031 - loss: 1.8221  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3106 - loss: 1.8463
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3159 - loss: 1.8457
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8485
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 1.8535
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 1.8583
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 1.8623
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 1.8637
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 1.8645
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 1.8651
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 1.8652
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 1.8650
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 1.8653
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 1.8654
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 1.8657
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 1.8658
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 1.8657
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 1.8654
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 1.8652
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 1.8650
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 1.8649
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 1.8647
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 1.8646
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 1.8645
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3160 - loss: 1.8643
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3161 - loss: 1.8641
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3163 - loss: 1.8640
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8638
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8638
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8638
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 1.8638
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8638
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 1.8638
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8637
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8636
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8634
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8633
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8632
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3187 - loss: 1.8631
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8629
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8628
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8626
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3192 - loss: 1.8624
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8623
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8623 - val_accuracy: 0.3308 - val_loss: 1.8576
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.7622
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3457 - loss: 1.8181  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8233
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3296 - loss: 1.8370
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3257 - loss: 1.8422
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 1.8450
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 1.8479
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8511
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8532
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8542
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8552
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8558
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8565
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8569
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8572
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3181 - loss: 1.8572
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8572
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8571
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3181 - loss: 1.8569
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8567
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8567
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8566
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3187 - loss: 1.8565
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8563
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 1.8563
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8562
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 1.8561
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8560
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 1.8557
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8555
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 1.8553
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 1.8550
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3210 - loss: 1.8548
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3212 - loss: 1.8546
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3215 - loss: 1.8543
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3217 - loss: 1.8541
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 1.8539
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 1.8536
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 1.8534
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 1.8533
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 1.8531
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 1.8529
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 1.8528
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 1.8527
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 1.8526
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 1.8525
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3235 - loss: 1.8524 - val_accuracy: 0.3486 - val_loss: 1.7834
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.7218
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3424 - loss: 1.7609  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3392 - loss: 1.7796
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3364 - loss: 1.7934
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3359 - loss: 1.7997
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8027
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8050
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3368 - loss: 1.8046
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8049
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8054
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8060
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3378 - loss: 1.8067
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8080
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8097
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8113
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8125
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8140
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8151
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8161
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8167
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8173
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8178
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8184
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8187
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8190
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8190
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8190
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8190
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8189
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8188
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8187
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8186
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8185
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8183
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8181
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8180
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8177
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.8175
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.8173
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8171
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8169
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3406 - loss: 1.8167
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3406 - loss: 1.8164
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8161
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8159 - val_accuracy: 0.3458 - val_loss: 1.7782
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7705
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8228  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3430 - loss: 1.8233
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3477 - loss: 1.8110
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3522 - loss: 1.8020
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7969
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7929
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7888
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7851
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7821
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7804
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7793
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7790
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7789
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7784
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7780
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7778
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7778
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7779
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7781
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7784
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7787
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7788
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7787
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7787
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7787
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7788
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7788
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7788
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7788
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7787
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7786
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7784
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7784
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7783
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7783
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7782
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7781
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7779
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7778
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7777
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7775
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7773
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7772
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7772
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7771 - val_accuracy: 0.3512 - val_loss: 1.8064
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.3278
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4242 - loss: 1.5951  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4050 - loss: 1.6280
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3926 - loss: 1.6593
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6777
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6892
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3811 - loss: 1.6965
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3789 - loss: 1.7029
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7079
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3758 - loss: 1.7123
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3744 - loss: 1.7158
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3732 - loss: 1.7193
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7220
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7240
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7256
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7272
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7288
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7305
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7320
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7332
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7344
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7356
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7366
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3677 - loss: 1.7376
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7384
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7392
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3673 - loss: 1.7399
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7406
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7411
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7418
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7423
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7427
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7431
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7434
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7437
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7438
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7439
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7440
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7441
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7442
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7443
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7444
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7445
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7447
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7449
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7451
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7451 - val_accuracy: 0.3502 - val_loss: 1.7967
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.5303
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4005 - loss: 1.6633  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3827 - loss: 1.7204
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7342
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7346
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7355
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3770 - loss: 1.7336
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7316
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7317
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7318
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3777 - loss: 1.7323
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3778 - loss: 1.7325
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3777 - loss: 1.7329
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7331
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7332
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3773 - loss: 1.7333
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7331
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3770 - loss: 1.7329
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3768 - loss: 1.7327
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7326
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7325
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3762 - loss: 1.7324
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3761 - loss: 1.7321
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3760 - loss: 1.7320
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7318
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3758 - loss: 1.7316
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3757 - loss: 1.7313
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3757 - loss: 1.7310
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3756 - loss: 1.7308
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.7305
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.7302
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7298
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7295
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7292
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3750 - loss: 1.7289
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3750 - loss: 1.7287
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3748 - loss: 1.7285
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3747 - loss: 1.7284
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3745 - loss: 1.7284
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3744 - loss: 1.7284
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3742 - loss: 1.7283
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7283
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3740 - loss: 1.7282
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3738 - loss: 1.7281
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3737 - loss: 1.7280
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3736 - loss: 1.7279
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7279 - val_accuracy: 0.3689 - val_loss: 1.7742
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2945
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3910 - loss: 1.6851  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3852 - loss: 1.6948
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3778 - loss: 1.6999
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7030
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7063
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7081
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7087
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3662 - loss: 1.7092
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7100
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7102
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7097
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7095
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7093
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7090
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3677 - loss: 1.7088
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3680 - loss: 1.7084
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7080
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7074
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7068
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3691 - loss: 1.7063
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7060
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7057
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7054
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3700 - loss: 1.7052
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3701 - loss: 1.7051
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7050
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3704 - loss: 1.7048
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7047
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7045
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7043
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7043
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7044
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7045
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7046
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7047
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7048
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7049
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7050
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7052
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7054
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7055
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7056
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7057
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7057
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7057 - val_accuracy: 0.3754 - val_loss: 1.7739
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3750 - loss: 1.5911
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3885 - loss: 1.5650  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3821 - loss: 1.5934
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3807 - loss: 1.6152
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6281
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3803 - loss: 1.6398
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.6505
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.6581
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6637
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3782 - loss: 1.6660
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.6684
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.6709
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.6729
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3779 - loss: 1.6743
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3776 - loss: 1.6754
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6765
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6772
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6777
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6781
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6786
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6792
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6797
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6801
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3773 - loss: 1.6805
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.6809
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6814
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6816
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6817
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6818
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3772 - loss: 1.6818
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3773 - loss: 1.6819
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6819
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.6821
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.6823
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.6825
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3776 - loss: 1.6828
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3776 - loss: 1.6831
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3776 - loss: 1.6834
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6837
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6840
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6843
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6845
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6847
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3778 - loss: 1.6849
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3778 - loss: 1.6851
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3779 - loss: 1.6852 - val_accuracy: 0.3280 - val_loss: 1.8507
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9254
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4334 - loss: 1.6525  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4222 - loss: 1.6549
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4114 - loss: 1.6602
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4075 - loss: 1.6602
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4054 - loss: 1.6593
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4042 - loss: 1.6590
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4032 - loss: 1.6588
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4021 - loss: 1.6600
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4014 - loss: 1.6609
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4004 - loss: 1.6619
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3993 - loss: 1.6631
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3984 - loss: 1.6637
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3977 - loss: 1.6639
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6643
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3965 - loss: 1.6648
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6653
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6656
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6658
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3949 - loss: 1.6659
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3946 - loss: 1.6661
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3944 - loss: 1.6661
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3942 - loss: 1.6661
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3941 - loss: 1.6661
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3940 - loss: 1.6660
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3938 - loss: 1.6660
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3937 - loss: 1.6660
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6662
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6663
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3933 - loss: 1.6664
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3932 - loss: 1.6664
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3931 - loss: 1.6662
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6660
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3929 - loss: 1.6659
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6657
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6656
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6655
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3926 - loss: 1.6653
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3925 - loss: 1.6652
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3924 - loss: 1.6651
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3923 - loss: 1.6649
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3923 - loss: 1.6648
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3922 - loss: 1.6646
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3922 - loss: 1.6645
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3921 - loss: 1.6643
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3921 - loss: 1.6642 - val_accuracy: 0.3702 - val_loss: 1.7727
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.4970
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3478 - loss: 1.7182  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3605 - loss: 1.6852
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3688 - loss: 1.6665
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3739 - loss: 1.6579
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3773 - loss: 1.6553
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3797 - loss: 1.6568
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3815 - loss: 1.6580
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6589
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3838 - loss: 1.6591
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6590
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3854 - loss: 1.6586
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6586
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3862 - loss: 1.6588
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6587
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3868 - loss: 1.6587
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6590
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3871 - loss: 1.6594
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3871 - loss: 1.6597
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3871 - loss: 1.6597
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3872 - loss: 1.6596
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3874 - loss: 1.6594
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3875 - loss: 1.6592
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3877 - loss: 1.6591
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6590
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3880 - loss: 1.6590
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3882 - loss: 1.6589
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3884 - loss: 1.6588
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3887 - loss: 1.6586
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3889 - loss: 1.6585
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3891 - loss: 1.6584
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3894 - loss: 1.6582
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3896 - loss: 1.6581
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3898 - loss: 1.6580
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3900 - loss: 1.6578
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3901 - loss: 1.6578
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3903 - loss: 1.6577
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3905 - loss: 1.6577
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3906 - loss: 1.6577
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6577
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6576
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3910 - loss: 1.6575
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3911 - loss: 1.6575
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3912 - loss: 1.6574
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3913 - loss: 1.6573
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3914 - loss: 1.6573 - val_accuracy: 0.3695 - val_loss: 1.7906

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 1s/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:35:15.377115: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:56[0m 1s/step
[1m 43/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m 98/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m156/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 978us/step
[1m212/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 956us/step
[1m267/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 948us/step
[1m325/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 935us/step
[1m381/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 931us/step
[1m440/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 921us/step
[1m489/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 932us/step
[1m542/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 933us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 977us/step
[1m 96/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m153/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 996us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 35.63 [%]
Global F1 score (validation) = 32.7 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.21243642 0.19708161 0.25159815 ... 0.00135209 0.1740779  0.0191884 ]
 [0.20873657 0.25437024 0.2161733  ... 0.00285303 0.14482875 0.01388671]
 [0.16217911 0.12002643 0.23154517 ... 0.00027606 0.16728455 0.02184592]
 ...
 [0.19580609 0.21335179 0.20663902 ... 0.00472792 0.13532472 0.00883015]
 [0.19154891 0.18741862 0.21159758 ... 0.00165696 0.13941485 0.00602107]
 [0.10668048 0.14327428 0.098807   ... 0.00823161 0.05608006 0.00491642]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 44.97 [%]
Global accuracy score (test) = 33.36 [%]
Global F1 score (train) = 41.97 [%]
Global F1 score (test) = 30.96 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.20      0.02      0.04       184
 CAMINAR CON MÓVIL O LIBRO       0.21      0.41      0.28       184
       CAMINAR USUAL SPEED       0.18      0.23      0.20       184
            CAMINAR ZIGZAG       0.42      0.62      0.50       184
          DE PIE BARRIENDO       0.24      0.29      0.26       184
   DE PIE DOBLANDO TOALLAS       0.28      0.17      0.22       184
    DE PIE MOVIENDO LIBROS       0.34      0.55      0.42       184
          DE PIE USANDO PC       0.28      0.66      0.39       184
        FASE REPOSO CON K5       1.00      0.55      0.71       184
INCREMENTAL CICLOERGOMETRO       0.70      0.54      0.61       184
           SENTADO LEYENDO       0.15      0.10      0.12       184
         SENTADO USANDO PC       0.00      0.00      0.00       184
      SENTADO VIENDO LA TV       0.41      0.42      0.42       184
   SUBIR Y BAJAR ESCALERAS       0.44      0.04      0.07       184
                    TROTAR       0.40      0.40      0.40       161

                  accuracy                           0.33      2737
                 macro avg       0.35      0.33      0.31      2737
              weighted avg       0.35      0.33      0.31      2737


Accuracy capturado en la ejecución 11: 33.36 [%]
F1-score capturado en la ejecución 11: 30.96 [%]

=== EJECUCIÓN 12 ===

--- TRAIN (ejecución 12) ---

--- TEST (ejecución 12) ---
2025-10-31 15:35:28.710820: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:35:28.722078: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761921328.735411 1680135 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761921328.739453 1680135 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761921328.749588 1680135 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921328.749608 1680135 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921328.749610 1680135 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921328.749612 1680135 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:35:28.752675: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761921331.147434 1680135 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761921334.225434 1680235 service.cc:152] XLA service 0x7430a8015e10 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761921334.225507 1680235 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:35:34.296102: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761921334.735186 1680235 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761921337.392256 1680235 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46:38[0m 5s/step - accuracy: 0.0625 - loss: 3.3414
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0676 - loss: 3.2440    
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0671 - loss: 3.2312
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0682 - loss: 3.2231
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0685 - loss: 3.2153
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0700 - loss: 3.2062
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0714 - loss: 3.1984
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0730 - loss: 3.1875
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0741 - loss: 3.1777
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0751 - loss: 3.1677
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0760 - loss: 3.1580
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0766 - loss: 3.1502
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0773 - loss: 3.1419
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0780 - loss: 3.1346
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0790 - loss: 3.1253
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0800 - loss: 3.1168
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0811 - loss: 3.1082
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0820 - loss: 3.1012
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0829 - loss: 3.0937
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0839 - loss: 3.0860
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0848 - loss: 3.0784
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0858 - loss: 3.0708
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0868 - loss: 3.0634
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0878 - loss: 3.0557
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0886 - loss: 3.0492
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0894 - loss: 3.0424
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0902 - loss: 3.0356
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0910 - loss: 3.0292
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0917 - loss: 3.0230
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0925 - loss: 3.0166
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0932 - loss: 3.0108
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0939 - loss: 3.0050
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0946 - loss: 2.9993
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0952 - loss: 2.9940
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0959 - loss: 2.9888
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0965 - loss: 2.9834
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0972 - loss: 2.9782
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0978 - loss: 2.9729
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0984 - loss: 2.9681
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0989 - loss: 2.9632
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0995 - loss: 2.9587
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0999 - loss: 2.9544
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1004 - loss: 2.9506
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1008 - loss: 2.9467
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1008 - loss: 2.9465 - val_accuracy: 0.1715 - val_loss: 2.3784
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.1250 - loss: 2.4654
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1625 - loss: 2.3887  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1597 - loss: 2.4343
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1582 - loss: 2.4588
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1576 - loss: 2.4733
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1558 - loss: 2.4830
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1542 - loss: 2.4890
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1533 - loss: 2.4933
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1528 - loss: 2.4944
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1529 - loss: 2.4938
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1531 - loss: 2.4928
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.4913
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1539 - loss: 2.4899
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1542 - loss: 2.4885
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1546 - loss: 2.4874
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1548 - loss: 2.4862
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4849
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1553 - loss: 2.4836
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4824
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1556 - loss: 2.4811
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1557 - loss: 2.4799
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1558 - loss: 2.4789
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1560 - loss: 2.4777
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1562 - loss: 2.4766
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1564 - loss: 2.4754
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1565 - loss: 2.4742
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1566 - loss: 2.4733
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1567 - loss: 2.4723
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1569 - loss: 2.4713
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1570 - loss: 2.4703
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1570 - loss: 2.4694
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1571 - loss: 2.4685
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1572 - loss: 2.4678
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1573 - loss: 2.4670
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4662
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4653
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1575 - loss: 2.4645
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1576 - loss: 2.4636
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1577 - loss: 2.4627
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1578 - loss: 2.4617
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1579 - loss: 2.4609
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1579 - loss: 2.4600
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1580 - loss: 2.4592
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1581 - loss: 2.4583
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1582 - loss: 2.4574
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1582 - loss: 2.4573 - val_accuracy: 0.1769 - val_loss: 2.2272
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1519
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1420 - loss: 2.3221  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1566 - loss: 2.3308
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1636 - loss: 2.3288
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1675 - loss: 2.3314
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1693 - loss: 2.3322
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1703 - loss: 2.3331
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3340
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1713 - loss: 2.3349
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1716 - loss: 2.3350
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3355
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3362
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1719 - loss: 2.3366
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3368
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3371
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3372
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3372
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1717 - loss: 2.3370
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1719 - loss: 2.3366
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1721 - loss: 2.3361
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1724 - loss: 2.3355
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3349
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1729 - loss: 2.3343
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1730 - loss: 2.3338
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1731 - loss: 2.3333
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1732 - loss: 2.3330
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1732 - loss: 2.3328
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1732 - loss: 2.3324
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1733 - loss: 2.3321
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1733 - loss: 2.3317
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1734 - loss: 2.3313
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1735 - loss: 2.3309
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1736 - loss: 2.3305
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1736 - loss: 2.3301
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1737 - loss: 2.3298
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1738 - loss: 2.3294
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1739 - loss: 2.3291
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1740 - loss: 2.3287
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1740 - loss: 2.3284
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1741 - loss: 2.3280
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1742 - loss: 2.3276
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1742 - loss: 2.3272
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1743 - loss: 2.3268
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1744 - loss: 2.3263
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1745 - loss: 2.3258
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1746 - loss: 2.3256 - val_accuracy: 0.1920 - val_loss: 2.1385
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9332
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2333 - loss: 2.1827  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2188 - loss: 2.2167
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2097 - loss: 2.2289
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2043 - loss: 2.2373
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2005 - loss: 2.2416
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1979 - loss: 2.2449
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1959 - loss: 2.2470
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1941 - loss: 2.2488
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1924 - loss: 2.2506
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1909 - loss: 2.2516
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1897 - loss: 2.2522
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1886 - loss: 2.2527
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1878 - loss: 2.2532
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1870 - loss: 2.2534
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2537
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2540
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2544
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1848 - loss: 2.2547
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1844 - loss: 2.2550
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1841 - loss: 2.2552
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2552
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2554
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2554
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2553
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2552
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2550
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2549
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2546
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2544
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2541
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2538
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2534
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2532
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2528
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2525
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1840 - loss: 2.2522
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1841 - loss: 2.2518
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1843 - loss: 2.2514
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1844 - loss: 2.2510
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2506
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2502
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.2498
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2493
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2491 - val_accuracy: 0.1994 - val_loss: 2.0516
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.0625 - loss: 2.3758
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1930 - loss: 2.2817  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1922 - loss: 2.2503
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2361
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1912 - loss: 2.2291
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1924 - loss: 2.2252
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1937 - loss: 2.2206
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1943 - loss: 2.2168
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1949 - loss: 2.2141
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1951 - loss: 2.2126
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1957 - loss: 2.2108
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1963 - loss: 2.2089
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1968 - loss: 2.2072
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1974 - loss: 2.2058
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1980 - loss: 2.2049
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1988 - loss: 2.2041
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1994 - loss: 2.2034
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1998 - loss: 2.2027
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2002 - loss: 2.2021
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2006 - loss: 2.2015
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2010
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2012 - loss: 2.2005
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2015 - loss: 2.1999
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2018 - loss: 2.1992
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.1986
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2024 - loss: 2.1980
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2027 - loss: 2.1974
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2030 - loss: 2.1969
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2033 - loss: 2.1963
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2035 - loss: 2.1959
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2037 - loss: 2.1954
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2039 - loss: 2.1950
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.1946
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2042 - loss: 2.1942
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.1939
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.1936
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2047 - loss: 2.1932
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2049 - loss: 2.1927
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2050 - loss: 2.1923
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2052 - loss: 2.1919
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2053 - loss: 2.1915
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2054 - loss: 2.1911
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2056 - loss: 2.1906
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.1902
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2059 - loss: 2.1898
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2059 - loss: 2.1897 - val_accuracy: 0.2148 - val_loss: 2.0250
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1516
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2168 - loss: 2.1226  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2232 - loss: 2.1105
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2218 - loss: 2.1108
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2220 - loss: 2.1140
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2229 - loss: 2.1152
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2231 - loss: 2.1162
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2233 - loss: 2.1173
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2238 - loss: 2.1177
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2240 - loss: 2.1188
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2239 - loss: 2.1192
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2239 - loss: 2.1191
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2239 - loss: 2.1187
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2240 - loss: 2.1186
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1185
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2245 - loss: 2.1182
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2248 - loss: 2.1179
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1177
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.1176
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2259 - loss: 2.1175
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2262 - loss: 2.1174
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2265 - loss: 2.1173
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2267 - loss: 2.1173
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2268 - loss: 2.1173
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2269 - loss: 2.1175
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2270 - loss: 2.1176
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2271 - loss: 2.1178
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2271 - loss: 2.1181
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2272 - loss: 2.1183
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2272 - loss: 2.1185
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2272 - loss: 2.1187
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2273 - loss: 2.1188
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2274 - loss: 2.1190
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2274 - loss: 2.1191
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2275 - loss: 2.1191
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2276 - loss: 2.1191
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2276 - loss: 2.1191
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2277 - loss: 2.1190
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2278 - loss: 2.1190
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2279 - loss: 2.1190
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2280 - loss: 2.1189
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2281 - loss: 2.1188
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2282 - loss: 2.1187
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2283 - loss: 2.1186
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2284 - loss: 2.1186 - val_accuracy: 0.2235 - val_loss: 2.0236
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9978
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2826 - loss: 2.0575  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0850
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0941
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2622 - loss: 2.0988
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2600 - loss: 2.1019
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2579 - loss: 2.1051
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2568 - loss: 2.1060
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.1051
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2562 - loss: 2.1033
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2561 - loss: 2.1018
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.1009
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2555 - loss: 2.1000
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2552 - loss: 2.0990
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2548 - loss: 2.0981
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2544 - loss: 2.0973
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2541 - loss: 2.0967
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.0960
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.0953
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0944
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0934
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0926
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0917
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0909
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0902
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2539 - loss: 2.0895
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2539 - loss: 2.0888
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2540 - loss: 2.0881
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2540 - loss: 2.0873
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.0865
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.0858
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.0851
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.0844
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2545 - loss: 2.0837
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2545 - loss: 2.0831
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.0826
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.0821
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.0816
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.0810
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2548 - loss: 2.0805
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2549 - loss: 2.0799
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.0794
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.0788
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2552 - loss: 2.0783
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2553 - loss: 2.0779 - val_accuracy: 0.3327 - val_loss: 1.9090
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1250 - loss: 2.1366
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2842 - loss: 1.9512  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9316
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2900 - loss: 1.9393
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2892 - loss: 1.9466
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2885 - loss: 1.9515
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2875 - loss: 1.9545
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 1.9560
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 1.9585
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 1.9604
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 1.9621
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 1.9636
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2855 - loss: 1.9654
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2853 - loss: 1.9670
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 1.9684
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 1.9698
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 1.9710
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 1.9724
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 1.9738
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 1.9753
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 1.9768
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 1.9783
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 1.9797
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 1.9808
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 1.9818
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2839 - loss: 1.9827
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 1.9835
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 1.9842
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2836 - loss: 1.9848
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 1.9854
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 1.9858
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 1.9861
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 1.9866
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9869
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 1.9872
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 1.9876
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9879
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9881
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9884
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9886
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9889
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9890
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9892
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9893
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9894 - val_accuracy: 0.3088 - val_loss: 1.8909
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.2500 - loss: 1.7604
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2887 - loss: 1.8483  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2986 - loss: 1.8662
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3003 - loss: 1.8899
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3000 - loss: 1.9072
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2995 - loss: 1.9176
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9255
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9302
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9339
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2976 - loss: 1.9372
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2971 - loss: 1.9403
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2966 - loss: 1.9425
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2966 - loss: 1.9436
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9445
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9462
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 1.9471
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 1.9480
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9487
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9491
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2950 - loss: 1.9496
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9503
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 1.9508
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 1.9513
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 1.9517
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 1.9522
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2931 - loss: 1.9528
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 1.9532
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 1.9535
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9537
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9539
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9540
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9542
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9544
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9546
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9547
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9549
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9550
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9552
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9553
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9554
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9554
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9555
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9555
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9554
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 1.9553
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2928 - loss: 1.9553 - val_accuracy: 0.3162 - val_loss: 1.8592
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1875 - loss: 2.0967
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2999 - loss: 1.8971  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3095 - loss: 1.8748
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3133 - loss: 1.8684
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 1.8727
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 1.8771
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 1.8823
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 1.8865
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 1.8897
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 1.8919
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8941
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.8955
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.8966
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.8979
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.8990
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.9000
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.9007
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 1.9012
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 1.9017
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 1.9020
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 1.9021
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 1.9023
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 1.9026
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 1.9028
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 1.9030
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 1.9032
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 1.9032
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 1.9033
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 1.9035
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 1.9038
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 1.9039
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 1.9041
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 1.9043
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 1.9045
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 1.9046
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 1.9048
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 1.9049
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 1.9049
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 1.9050
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 1.9051
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 1.9051
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 1.9051
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.9052
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.9052
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.9052
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3114 - loss: 1.9052 - val_accuracy: 0.3249 - val_loss: 1.8313
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.8712
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3157 - loss: 1.8330  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3069 - loss: 1.8696
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3064 - loss: 1.8809
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3066 - loss: 1.8868
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 1.8916
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3085 - loss: 1.8942
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 1.8967
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 1.8983
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 1.8992
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 1.8993
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 1.8995
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 1.8999
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 1.9000
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 1.9002
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3068 - loss: 1.9002
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3066 - loss: 1.9004
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3065 - loss: 1.9006
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9007
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9008
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9010
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9012
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3065 - loss: 1.9014
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3066 - loss: 1.9017
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3067 - loss: 1.9019
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 1.9021
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 1.9022
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 1.9023
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 1.9024
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 1.9025
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 1.9024
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 1.9023
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 1.9023
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 1.9022
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 1.9020
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3072 - loss: 1.9018
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3073 - loss: 1.9016
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3074 - loss: 1.9014
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 1.9013
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3076 - loss: 1.9010
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3078 - loss: 1.9007
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3079 - loss: 1.9005
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3080 - loss: 1.9002
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3082 - loss: 1.9000
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3083 - loss: 1.8998 - val_accuracy: 0.3571 - val_loss: 1.8024
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.7728
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2852 - loss: 1.8394  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2897 - loss: 1.8574
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2952 - loss: 1.8558
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 1.8570
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3032 - loss: 1.8588
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3054 - loss: 1.8600
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 1.8599
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 1.8602
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3100 - loss: 1.8608
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8617
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 1.8636
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 1.8649
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 1.8657
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 1.8663
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 1.8668
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.8670
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 1.8672
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 1.8672
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 1.8671
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 1.8670
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 1.8669
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 1.8668
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 1.8669
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 1.8670
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 1.8669
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 1.8668
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3155 - loss: 1.8668
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3157 - loss: 1.8667
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3159 - loss: 1.8665
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3161 - loss: 1.8663
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3163 - loss: 1.8661
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8659
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3167 - loss: 1.8657
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8654
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8652
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8650
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8648
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8647
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8645
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8643
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 1.8642
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8640
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8638
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3186 - loss: 1.8636 - val_accuracy: 0.3288 - val_loss: 1.8064
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 1.8893
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2761 - loss: 1.8985  
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9004
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3057 - loss: 1.8954
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3072 - loss: 1.8924
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3086 - loss: 1.8887
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3091 - loss: 1.8865
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 1.8841
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 1.8805
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3120 - loss: 1.8775
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.8745
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 1.8722
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 1.8702
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 1.8685
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8670
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8653
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8636
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8621
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 1.8609
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8595
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3209 - loss: 1.8581
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 1.8571
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 1.8560
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 1.8549
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 1.8537
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 1.8525
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8514
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8504
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 1.8495
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 1.8487
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 1.8480
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 1.8474
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 1.8468
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 1.8462
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3265 - loss: 1.8455
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 1.8449
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 1.8444
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3271 - loss: 1.8438
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 1.8432
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 1.8426
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 1.8421
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3278 - loss: 1.8417
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 1.8414
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3281 - loss: 1.8410
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3283 - loss: 1.8406 - val_accuracy: 0.3328 - val_loss: 1.8142
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3728
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3478 - loss: 1.8640  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3490 - loss: 1.8298
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3535 - loss: 1.8062
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7944
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3532 - loss: 1.7908
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7884
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3505 - loss: 1.7868
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7864
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3489 - loss: 1.7867
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3481 - loss: 1.7875
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7883
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7889
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7895
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3475 - loss: 1.7899
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3474 - loss: 1.7904
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.7910
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.7913
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.7918
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3474 - loss: 1.7920
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3475 - loss: 1.7921
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7921
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7923
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7925
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7926
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7927
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7928
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7931
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3475 - loss: 1.7933
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3474 - loss: 1.7935
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3473 - loss: 1.7937
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.7940
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7941
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7941
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7941
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3470 - loss: 1.7941
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3470 - loss: 1.7941
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7941
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7941
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7941
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7941
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7941
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7942
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7943
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7943 - val_accuracy: 0.3321 - val_loss: 1.8337
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.7968
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3139 - loss: 1.8466  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3211 - loss: 1.8290
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3293 - loss: 1.8166
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3346 - loss: 1.8144
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8125
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8113
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8110
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3409 - loss: 1.8105
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3411 - loss: 1.8108
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8102
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8095
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.8090
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8084
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3429 - loss: 1.8078
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.8072
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3438 - loss: 1.8064
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3443 - loss: 1.8055
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3447 - loss: 1.8046
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.8037
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3455 - loss: 1.8028
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3458 - loss: 1.8019
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3461 - loss: 1.8010
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3464 - loss: 1.8001
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3466 - loss: 1.7995
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3469 - loss: 1.7989
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7982
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.7976
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3474 - loss: 1.7971
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3475 - loss: 1.7965
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7960
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7956
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3478 - loss: 1.7951
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7946
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3480 - loss: 1.7941
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3481 - loss: 1.7937
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3481 - loss: 1.7932
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7928
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7925
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7922
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3483 - loss: 1.7919
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3483 - loss: 1.7916
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3483 - loss: 1.7912
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3483 - loss: 1.7910
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3484 - loss: 1.7907 - val_accuracy: 0.3889 - val_loss: 1.7808
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3125 - loss: 1.8589
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3460 - loss: 1.7071  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3402 - loss: 1.7369
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3453 - loss: 1.7360
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7315
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7290
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7269
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7259
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7252
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7240
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7231
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7217
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7207
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7202
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7198
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7193
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7193
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7196
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7201
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7207
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7213
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7218
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7226
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7234
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7242
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7250
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7258
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7265
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7271
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7277
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7282
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7288
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7294
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7299
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7304
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7309
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7314
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7318
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7323
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7328
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7333
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7338
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7342
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7345
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7348
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7349 - val_accuracy: 0.4065 - val_loss: 1.7755
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.8416
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3873 - loss: 1.7571  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7745
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3692 - loss: 1.7798
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7803
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7751
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3701 - loss: 1.7714
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7694
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7692
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7681
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7671
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7659
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7651
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7644
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7636
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7629
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7622
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7615
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7607
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7599
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7590
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7579
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7569
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7559
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7548
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3687 - loss: 1.7537
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7527
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7519
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7511
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7503
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7496
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7489
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7484
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7480
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7476
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7472
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7468
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3687 - loss: 1.7465
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3687 - loss: 1.7461
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7458
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7455
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7451
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7449
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7446
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7445 - val_accuracy: 0.3904 - val_loss: 1.7663
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.5259
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3908 - loss: 1.7032  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3910 - loss: 1.7077
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3910 - loss: 1.7028
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3900 - loss: 1.7015
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3888 - loss: 1.7016
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3877 - loss: 1.7018
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3863 - loss: 1.7028
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3850 - loss: 1.7035
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3838 - loss: 1.7042
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3828 - loss: 1.7046
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3821 - loss: 1.7043
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3817 - loss: 1.7035
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3811 - loss: 1.7032
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3804 - loss: 1.7032
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3797 - loss: 1.7036
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3792 - loss: 1.7041
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3788 - loss: 1.7043
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.7045
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7043
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.7043
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3779 - loss: 1.7044
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3777 - loss: 1.7046
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7046
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7047
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7047
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7047
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7049
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3768 - loss: 1.7050
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3768 - loss: 1.7050
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7050
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7049
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.7049
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.7049
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7049
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7050
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7051
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.7052
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.7052
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.7053
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7054
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7054
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7054
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7054
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7054
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7055 - val_accuracy: 0.3584 - val_loss: 1.7947
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7940
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3579 - loss: 1.8848  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3705 - loss: 1.8142
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7863
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7732
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7663
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7613
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7577
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7537
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3701 - loss: 1.7496
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7463
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3692 - loss: 1.7437
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3691 - loss: 1.7409
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7387
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7366
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7344
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3691 - loss: 1.7322
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7305
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7289
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7275
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7262
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3700 - loss: 1.7250
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7241
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7233
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7227
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3704 - loss: 1.7220
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7213
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7205
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7198
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7192
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7186
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7182
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7176
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7172
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7168
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7164
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7159
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7155
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7150
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7146
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7142
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7137
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7132
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7128
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7124 - val_accuracy: 0.3946 - val_loss: 1.7763
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.3750 - loss: 1.5037
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4062 - loss: 1.6308  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4062 - loss: 1.6224
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4072 - loss: 1.6284
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4065 - loss: 1.6407
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4060 - loss: 1.6466
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4057 - loss: 1.6472
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4057 - loss: 1.6470
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4052 - loss: 1.6493
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4044 - loss: 1.6519
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4038 - loss: 1.6536
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4035 - loss: 1.6545
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4029 - loss: 1.6563
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4020 - loss: 1.6582
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4013 - loss: 1.6597
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4005 - loss: 1.6611
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3998 - loss: 1.6622
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3992 - loss: 1.6633
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3987 - loss: 1.6641
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6647
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3978 - loss: 1.6650
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3974 - loss: 1.6652
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6653
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6654
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6654
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3964 - loss: 1.6654
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3962 - loss: 1.6655
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3959 - loss: 1.6657
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3957 - loss: 1.6659
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6661
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6663
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6665
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3949 - loss: 1.6667
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3948 - loss: 1.6669
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3946 - loss: 1.6671
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3944 - loss: 1.6672
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3943 - loss: 1.6672
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3942 - loss: 1.6673
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3941 - loss: 1.6674
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3939 - loss: 1.6676
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3938 - loss: 1.6677
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3937 - loss: 1.6678
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6680
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6681
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3933 - loss: 1.6682 - val_accuracy: 0.4028 - val_loss: 1.7756
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.7222
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7300  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3625 - loss: 1.6981
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3658 - loss: 1.6778
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3675 - loss: 1.6699
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3680 - loss: 1.6685
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3691 - loss: 1.6668
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.6669
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.6657
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3717 - loss: 1.6653
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3723 - loss: 1.6649
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3729 - loss: 1.6647
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3736 - loss: 1.6640
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3742 - loss: 1.6632
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3747 - loss: 1.6626
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3751 - loss: 1.6620
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3755 - loss: 1.6615
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3758 - loss: 1.6613
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3762 - loss: 1.6610
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6609
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.6608
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.6607
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.6605
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3778 - loss: 1.6605
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3779 - loss: 1.6606
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3780 - loss: 1.6608
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3781 - loss: 1.6609
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.6608
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.6608
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3787 - loss: 1.6608
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3788 - loss: 1.6608
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3790 - loss: 1.6608
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3791 - loss: 1.6608
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3793 - loss: 1.6608
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3794 - loss: 1.6608
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6607
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3797 - loss: 1.6607
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3798 - loss: 1.6606
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3799 - loss: 1.6606
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3800 - loss: 1.6605
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3801 - loss: 1.6604
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3802 - loss: 1.6604
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3803 - loss: 1.6603
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3805 - loss: 1.6603
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3806 - loss: 1.6602
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3807 - loss: 1.6601 - val_accuracy: 0.3952 - val_loss: 1.7966

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:33[0m 1s/step
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 920us/step2025-10-31 15:36:41.133372: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:01[0m 1s/step
[1m 49/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m106/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 960us/step
[1m159/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 956us/step
[1m213/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 952us/step
[1m273/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 928us/step
[1m331/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 918us/step
[1m389/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 913us/step
[1m447/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 908us/step
[1m505/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 903us/step
[1m557/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 910us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 976us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 980us/step
[1m110/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 919us/step
[1m167/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 905us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 36.95 [%]
Global F1 score (validation) = 33.23 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.2227611  0.2582248  0.18378182 ... 0.0041838  0.1293426  0.0145471 ]
 [0.24335001 0.2503419  0.19797036 ... 0.00600613 0.14212683 0.02137967]
 [0.2590327  0.2053114  0.1925023  ... 0.00454454 0.17449011 0.06197357]
 ...
 [0.2573722  0.2576795  0.19329368 ... 0.00413498 0.14616768 0.02170284]
 [0.22159077 0.26060146 0.18738212 ... 0.00224606 0.13412572 0.0108949 ]
 [0.20329028 0.20658535 0.18831456 ... 0.00104197 0.17627673 0.0191111 ]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.12 [%]
Global accuracy score (test) = 32.92 [%]
Global F1 score (train) = 41.9 [%]
Global F1 score (test) = 30.01 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.15      0.19      0.17       184
 CAMINAR CON MÓVIL O LIBRO       0.20      0.47      0.28       184
       CAMINAR USUAL SPEED       0.00      0.00      0.00       184
            CAMINAR ZIGZAG       0.48      0.51      0.50       184
          DE PIE BARRIENDO       0.27      0.36      0.31       184
   DE PIE DOBLANDO TOALLAS       0.35      0.08      0.13       184
    DE PIE MOVIENDO LIBROS       0.33      0.65      0.43       184
          DE PIE USANDO PC       0.30      0.63      0.41       184
        FASE REPOSO CON K5       0.83      0.62      0.71       184
INCREMENTAL CICLOERGOMETRO       0.80      0.57      0.67       184
           SENTADO LEYENDO       0.19      0.23      0.21       184
         SENTADO USANDO PC       0.20      0.18      0.19       184
      SENTADO VIENDO LA TV       0.67      0.02      0.04       184
   SUBIR Y BAJAR ESCALERAS       0.60      0.03      0.06       184
                    TROTAR       0.39      0.40      0.39       161

                  accuracy                           0.33      2737
                 macro avg       0.38      0.33      0.30      2737
              weighted avg       0.38      0.33      0.30      2737


Accuracy capturado en la ejecución 12: 32.92 [%]
F1-score capturado en la ejecución 12: 30.01 [%]

=== EJECUCIÓN 13 ===

--- TRAIN (ejecución 13) ---

--- TEST (ejecución 13) ---
2025-10-31 15:36:54.395854: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:36:54.407240: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761921414.420636 1683599 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761921414.424941 1683599 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761921414.435014 1683599 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921414.435036 1683599 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921414.435038 1683599 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921414.435040 1683599 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:36:54.438390: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761921416.813216 1683599 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761921419.970538 1683715 service.cc:152] XLA service 0x75283c002320 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761921419.970616 1683715 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:37:00.038922: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761921420.457170 1683715 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761921423.104595 1683715 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:07[0m 6s/step - accuracy: 0.1250 - loss: 3.3379
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0823 - loss: 3.2941    
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0809 - loss: 3.2919
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0808 - loss: 3.2758
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0816 - loss: 3.2613
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0829 - loss: 3.2460
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0848 - loss: 3.2329
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0860 - loss: 3.2207
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0867 - loss: 3.2092
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0872 - loss: 3.1999
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0877 - loss: 3.1914
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0882 - loss: 3.1832
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0888 - loss: 3.1751
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0894 - loss: 3.1677
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0902 - loss: 3.1599
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0909 - loss: 3.1528
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0917 - loss: 3.1453
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0925 - loss: 3.1373
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0932 - loss: 3.1302
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0938 - loss: 3.1238
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0946 - loss: 3.1159
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0952 - loss: 3.1089
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0958 - loss: 3.1019
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0964 - loss: 3.0949
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0969 - loss: 3.0884
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0974 - loss: 3.0821
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0979 - loss: 3.0767
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0983 - loss: 3.0705
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0988 - loss: 3.0645
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0993 - loss: 3.0590
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0997 - loss: 3.0532
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1002 - loss: 3.0478
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1007 - loss: 3.0424
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1011 - loss: 3.0371
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1015 - loss: 3.0328
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1020 - loss: 3.0277
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1024 - loss: 3.0229
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1028 - loss: 3.0182
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1032 - loss: 3.0135
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1036 - loss: 3.0086
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1040 - loss: 3.0041
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1045 - loss: 2.9997
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1048 - loss: 2.9957
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1052 - loss: 2.9919
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1055 - loss: 2.9879
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1057 - loss: 2.9857
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 7ms/step - accuracy: 0.1057 - loss: 2.9855 - val_accuracy: 0.1697 - val_loss: 2.3602
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1250 - loss: 2.7878
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1630 - loss: 2.4904  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1611 - loss: 2.4926
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1614 - loss: 2.5011
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1581 - loss: 2.5103
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1554 - loss: 2.5137
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1537 - loss: 2.5154
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1524 - loss: 2.5173
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1515 - loss: 2.5187
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1509 - loss: 2.5196
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1502 - loss: 2.5202
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1497 - loss: 2.5206
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1490 - loss: 2.5214
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1487 - loss: 2.5218
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1483 - loss: 2.5218
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1482 - loss: 2.5214
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1482 - loss: 2.5208
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5200
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5191
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1480 - loss: 2.5182
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1480 - loss: 2.5174
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1480 - loss: 2.5165
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5155
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5144
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5135
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5127
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5117
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5107
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1482 - loss: 2.5098
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1482 - loss: 2.5088
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1482 - loss: 2.5078
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1483 - loss: 2.5068
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1484 - loss: 2.5058
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1484 - loss: 2.5049
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1485 - loss: 2.5038
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1486 - loss: 2.5026
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1488 - loss: 2.5014
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1489 - loss: 2.5002
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1490 - loss: 2.4992
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1491 - loss: 2.4981
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1492 - loss: 2.4970
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1493 - loss: 2.4959
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1495 - loss: 2.4948
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1496 - loss: 2.4938
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1497 - loss: 2.4927
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1498 - loss: 2.4921 - val_accuracy: 0.1776 - val_loss: 2.2105
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1287
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2620  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1744 - loss: 2.3050
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1724 - loss: 2.3161
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1725 - loss: 2.3217
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1725 - loss: 2.3246
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1721 - loss: 2.3284
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3327
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1706 - loss: 2.3356
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1706 - loss: 2.3367
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1706 - loss: 2.3372
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3374
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3377
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1710 - loss: 2.3383
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3391
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3399
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3407
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3415
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3420
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3424
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3427
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3430
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3431
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3431
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3431
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1713 - loss: 2.3429
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3427
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3424
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1716 - loss: 2.3421
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3418
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1719 - loss: 2.3416
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1720 - loss: 2.3413
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1722 - loss: 2.3411
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1723 - loss: 2.3408
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1724 - loss: 2.3406
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1725 - loss: 2.3403
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1726 - loss: 2.3401
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3399
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3397
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3395
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3393
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3391
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3388
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3385
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1728 - loss: 2.3383
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1728 - loss: 2.3382 - val_accuracy: 0.2000 - val_loss: 2.1268
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4744
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2059 - loss: 2.3077  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1918 - loss: 2.3103
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1881 - loss: 2.3047
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1863 - loss: 2.3032
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1847 - loss: 2.3043
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1838 - loss: 2.3044
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.3036
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1842 - loss: 2.3010
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2984
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2966
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2952
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2936
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2920
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2902
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2891
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2877
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2866
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2854
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2844
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2835
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2824
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2815
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2805
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2796
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2787
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2778
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1858 - loss: 2.2769
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1858 - loss: 2.2760
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.2752
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.2742
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1861 - loss: 2.2734
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.2727
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2720
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.2713
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1865 - loss: 2.2706
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1866 - loss: 2.2698
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1867 - loss: 2.2691
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1867 - loss: 2.2685
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1868 - loss: 2.2679
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1868 - loss: 2.2673
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1869 - loss: 2.2668
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1869 - loss: 2.2661
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1870 - loss: 2.2655
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1870 - loss: 2.2650
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1871 - loss: 2.2647 - val_accuracy: 0.2346 - val_loss: 2.0541
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.8840
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2504 - loss: 2.1218  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2326 - loss: 2.1649
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2239 - loss: 2.1754
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2191 - loss: 2.1779
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2171 - loss: 2.1772
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2150 - loss: 2.1796
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2125 - loss: 2.1842
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2105 - loss: 2.1877
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2091 - loss: 2.1902
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2080 - loss: 2.1918
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2071 - loss: 2.1932
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2065 - loss: 2.1940
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2061 - loss: 2.1946
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2058 - loss: 2.1948
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2057 - loss: 2.1947
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2056 - loss: 2.1944
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2057 - loss: 2.1940
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2058 - loss: 2.1938
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2058 - loss: 2.1937
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2058 - loss: 2.1938
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2059 - loss: 2.1939
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2060 - loss: 2.1938
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2061 - loss: 2.1935
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2063 - loss: 2.1932
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2064 - loss: 2.1929
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2066 - loss: 2.1925
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2067 - loss: 2.1923
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2068 - loss: 2.1922
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2069 - loss: 2.1921
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2070 - loss: 2.1920
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2072 - loss: 2.1919
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2073 - loss: 2.1918
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2074 - loss: 2.1916
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.1915
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2076 - loss: 2.1914
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2077 - loss: 2.1913
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2078 - loss: 2.1911
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2079 - loss: 2.1910
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2080 - loss: 2.1909
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2081 - loss: 2.1907
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.1906
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2083 - loss: 2.1905
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2084 - loss: 2.1903
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2085 - loss: 2.1901
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2086 - loss: 2.1900 - val_accuracy: 0.2514 - val_loss: 2.0107
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9359
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1997 - loss: 2.1173  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2057 - loss: 2.1395
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2066 - loss: 2.1486
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2073 - loss: 2.1526
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2092 - loss: 2.1569
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1586
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2126 - loss: 2.1592
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2136 - loss: 2.1595
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2141 - loss: 2.1599
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.1598
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2153 - loss: 2.1599
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2159 - loss: 2.1596
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2168 - loss: 2.1590
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.1580
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1569
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2193 - loss: 2.1557
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2198 - loss: 2.1549
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2203 - loss: 2.1540
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2206 - loss: 2.1532
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2210 - loss: 2.1525
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.1520
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2215 - loss: 2.1514
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2217 - loss: 2.1508
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2220 - loss: 2.1502
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2222 - loss: 2.1496
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2224 - loss: 2.1491
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2226 - loss: 2.1488
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2227 - loss: 2.1484
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.1481
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2231 - loss: 2.1477
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2233 - loss: 2.1473
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2234 - loss: 2.1468
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1463
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2238 - loss: 2.1458
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1452
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2243 - loss: 2.1447
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.1441
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2248 - loss: 2.1435
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2251 - loss: 2.1429
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2253 - loss: 2.1423
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2256 - loss: 2.1417
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2258 - loss: 2.1412
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2260 - loss: 2.1407
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2263 - loss: 2.1401
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2265 - loss: 2.1396
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2265 - loss: 2.1395 - val_accuracy: 0.3378 - val_loss: 1.9250
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.0625 - loss: 2.0183
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2362 - loss: 2.1004  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2487 - loss: 2.0824
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0780
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2526 - loss: 2.0774
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.0795
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0809
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2503 - loss: 2.0806
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2503 - loss: 2.0802
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0800
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.0800
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.0801
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.0800
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0799
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2520 - loss: 2.0796
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2524 - loss: 2.0793
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2527 - loss: 2.0790
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2531 - loss: 2.0786
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2534 - loss: 2.0781
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2537 - loss: 2.0776
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.0770
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.0765
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.0759
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2549 - loss: 2.0752
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2552 - loss: 2.0747
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.0742
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.0737
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2558 - loss: 2.0731
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2560 - loss: 2.0726
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.0720
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2563 - loss: 2.0715
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2564 - loss: 2.0710
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2566 - loss: 2.0706
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2567 - loss: 2.0702
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2569 - loss: 2.0697
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2570 - loss: 2.0691
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2572 - loss: 2.0686
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2573 - loss: 2.0680
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2574 - loss: 2.0675
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2576 - loss: 2.0670
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.0665
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.0659
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2580 - loss: 2.0654
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.0650
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2583 - loss: 2.0646
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.0641
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2585 - loss: 2.0640 - val_accuracy: 0.2975 - val_loss: 1.9125
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1250 - loss: 1.8758
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2822 - loss: 2.0022  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2793 - loss: 2.0231
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2769 - loss: 2.0272
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2765 - loss: 2.0266
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2777 - loss: 2.0249
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 2.0238
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2784 - loss: 2.0232
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 2.0223
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2791 - loss: 2.0229
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.0226
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.0223
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.0220
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.0216
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2801 - loss: 2.0208
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2801 - loss: 2.0200
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.0190
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.0181
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.0174
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2801 - loss: 2.0168
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.0163
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.0158
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.0153
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.0150
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.0146
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.0142
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.0136
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.0131
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.0126
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.0120
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.0115
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.0110
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.0105
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.0099
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.0094
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.0089
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.0084
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.0079
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.0074
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.0069
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 2.0064
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 2.0059
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2801 - loss: 2.0053
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 2.0047
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.0042
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2803 - loss: 2.0039 - val_accuracy: 0.3493 - val_loss: 1.8244
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 1.7696
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3056 - loss: 1.9087  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3033 - loss: 1.9303
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3002 - loss: 1.9424
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9489
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9503
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2989 - loss: 1.9497
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2991 - loss: 1.9499
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2989 - loss: 1.9503
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9507
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9511
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2976 - loss: 1.9514
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9515
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 1.9513
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 1.9512
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9509
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 1.9508
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9508
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9507
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2966 - loss: 1.9504
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2966 - loss: 1.9503
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 1.9501
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9498
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 1.9496
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 1.9493
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 1.9491
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 1.9489
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2971 - loss: 1.9487
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9485
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2974 - loss: 1.9483
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2975 - loss: 1.9480
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9477
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2978 - loss: 1.9475
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 1.9474
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9473
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9473
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9473
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 1.9473
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9472
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9471
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9470
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9468
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9467
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2988 - loss: 1.9465
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 1.9463
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2990 - loss: 1.9461 - val_accuracy: 0.3608 - val_loss: 1.7809
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.5719
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2816 - loss: 1.9181  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2870 - loss: 1.9343
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9382
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2967 - loss: 1.9357
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3000 - loss: 1.9333
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3024 - loss: 1.9301
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 1.9259
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3062 - loss: 1.9225
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 1.9197
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 1.9175
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9157
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 1.9144
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 1.9126
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3120 - loss: 1.9114
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 1.9106
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 1.9098
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 1.9092
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 1.9085
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 1.9079
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 1.9075
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 1.9070
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9065
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9060
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 1.9056
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 1.9051
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 1.9047
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3155 - loss: 1.9044
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9042
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9041
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9039
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9037
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9036
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9034
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9031
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9029
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9027
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9025
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9023
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9021
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3157 - loss: 1.9020
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3157 - loss: 1.9018
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3157 - loss: 1.9016
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3157 - loss: 1.9015
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3157 - loss: 1.9015 - val_accuracy: 0.3569 - val_loss: 1.7802
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.2038
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2869 - loss: 2.0441  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3015 - loss: 1.9934
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3082 - loss: 1.9648
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3109 - loss: 1.9476
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3115 - loss: 1.9354
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.9253
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 1.9161
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 1.9086
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3174 - loss: 1.9031
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8995
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3186 - loss: 1.8970
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8949
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8936
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8927
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8918
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 1.8906
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3209 - loss: 1.8896
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 1.8889
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 1.8884
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3213 - loss: 1.8879
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 1.8874
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3216 - loss: 1.8870
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 1.8864
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3220 - loss: 1.8861
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 1.8857
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 1.8853
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.8849
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3228 - loss: 1.8845
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 1.8841
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 1.8837
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 1.8833
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 1.8829
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 1.8825
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 1.8821
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 1.8817
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 1.8813
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 1.8810
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8806
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8804
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8800
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8797
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8793
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8790
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8787
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8785 - val_accuracy: 0.3545 - val_loss: 1.7742
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.4866
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3409 - loss: 1.9221  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3382 - loss: 1.9186
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3395 - loss: 1.9091
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3404 - loss: 1.8964
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3412 - loss: 1.8856
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8761
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8689
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3420 - loss: 1.8635
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.8594
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.8561
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8538
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8519
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8501
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3411 - loss: 1.8485
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3409 - loss: 1.8469
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8457
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8449
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8441
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8434
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8427
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8419
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8413
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8408
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8401
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8395
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8389
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8385
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8382
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8379
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8376
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8374
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8371
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8369
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8368
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8366
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8364
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8362
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8361
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8360
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8359
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8358
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8357
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8356
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8355 - val_accuracy: 0.3362 - val_loss: 1.7544
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1250 - loss: 2.5647
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2918 - loss: 1.9657  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3111 - loss: 1.9198
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8954
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3254 - loss: 1.8834
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8746
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8675
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8642
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 1.8618
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8595
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8575
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3348 - loss: 1.8552
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3352 - loss: 1.8530
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3356 - loss: 1.8511
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8495
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8483
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8473
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8465
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.8456
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8445
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3373 - loss: 1.8435
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3376 - loss: 1.8426
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3378 - loss: 1.8418
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8410
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8402
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8395
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8387
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8378
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8370
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8362
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8354
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8346
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8337
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8328
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8319
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3406 - loss: 1.8311
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3408 - loss: 1.8305
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8298
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3411 - loss: 1.8292
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8287
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8281
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8276
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8270
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8265
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8261
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3420 - loss: 1.8256 - val_accuracy: 0.3624 - val_loss: 1.7470
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 1.9798
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3136 - loss: 1.8130  
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3345 - loss: 1.7911
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3431 - loss: 1.7797
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7754
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7757
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3475 - loss: 1.7767
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3469 - loss: 1.7783
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 1.7787
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3458 - loss: 1.7791
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3458 - loss: 1.7794
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7800
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7804
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3453 - loss: 1.7809
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7813
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3450 - loss: 1.7815
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3448 - loss: 1.7816
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3448 - loss: 1.7812
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3449 - loss: 1.7809
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3449 - loss: 1.7805
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3450 - loss: 1.7803
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.7800
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.7799
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7796
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7792
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3453 - loss: 1.7789
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3453 - loss: 1.7786
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7783
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7779
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3457 - loss: 1.7777
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3459 - loss: 1.7775
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3460 - loss: 1.7773
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3462 - loss: 1.7772
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3464 - loss: 1.7771
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3465 - loss: 1.7770
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3467 - loss: 1.7769
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3468 - loss: 1.7769
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3470 - loss: 1.7768
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7768
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3473 - loss: 1.7767
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3474 - loss: 1.7767
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3475 - loss: 1.7767
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7767
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3478 - loss: 1.7767
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7767
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3479 - loss: 1.7766 - val_accuracy: 0.3759 - val_loss: 1.7670
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3750 - loss: 1.5117
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3449 - loss: 1.7685  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3431 - loss: 1.7436
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7431
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3467 - loss: 1.7455
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7524
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.7573
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3431 - loss: 1.7606
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.7631
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.7641
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3442 - loss: 1.7648
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3446 - loss: 1.7656
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.7661
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3457 - loss: 1.7662
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3464 - loss: 1.7660
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.7654
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7646
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3490 - loss: 1.7640
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7635
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7633
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3507 - loss: 1.7631
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3511 - loss: 1.7632
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7632
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7632
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3522 - loss: 1.7630
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7629
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7628
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3531 - loss: 1.7627
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7626
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7625
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7623
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7621
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3541 - loss: 1.7619
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7617
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7615
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7614
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7613
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7612
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7610
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7608
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3553 - loss: 1.7606
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3553 - loss: 1.7604
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7603
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3555 - loss: 1.7601
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3556 - loss: 1.7600
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3556 - loss: 1.7599 - val_accuracy: 0.3624 - val_loss: 1.7637
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.0059
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3423 - loss: 1.7678  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7408
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7381
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7380
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7373
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7361
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7349
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7338
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7324
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7319
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7317
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7321
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7326
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7331
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7334
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7337
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7340
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7344
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7349
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7355
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7362
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7369
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7375
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7380
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7385
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7388
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7392
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7394
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7395
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7396
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7397
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7396
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7396
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7397
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7397
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7397
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7397
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7396
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7395
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7394
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7393
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7393
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7393
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7392
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7392
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7392 - val_accuracy: 0.3719 - val_loss: 1.7457
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0624
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6917  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3996 - loss: 1.6652
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6575
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4013 - loss: 1.6563
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3992 - loss: 1.6594
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3974 - loss: 1.6626
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3957 - loss: 1.6658
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3944 - loss: 1.6681
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3937 - loss: 1.6700
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3936 - loss: 1.6713
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6728
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3929 - loss: 1.6745
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3924 - loss: 1.6765
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6788
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3912 - loss: 1.6810
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6830
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3903 - loss: 1.6848
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3901 - loss: 1.6862
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3899 - loss: 1.6875
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3897 - loss: 1.6888
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3896 - loss: 1.6898
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3894 - loss: 1.6907
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3894 - loss: 1.6914
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3893 - loss: 1.6919
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3893 - loss: 1.6924
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3892 - loss: 1.6929
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3891 - loss: 1.6934
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3891 - loss: 1.6939
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3890 - loss: 1.6942
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3890 - loss: 1.6946
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3890 - loss: 1.6949
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3890 - loss: 1.6952
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3890 - loss: 1.6954
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3889 - loss: 1.6956
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3889 - loss: 1.6958
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3888 - loss: 1.6960
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3887 - loss: 1.6961
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3887 - loss: 1.6963
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3886 - loss: 1.6964
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3885 - loss: 1.6965
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3885 - loss: 1.6967
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3884 - loss: 1.6968
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3883 - loss: 1.6970
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3882 - loss: 1.6971
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3881 - loss: 1.6973 - val_accuracy: 0.3573 - val_loss: 1.7805
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.3046
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3990 - loss: 1.6593  
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3929 - loss: 1.6746
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3933 - loss: 1.6769
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6756
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6759
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3977 - loss: 1.6765
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6780
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3957 - loss: 1.6809
[1m 226/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3948 - loss: 1.6826
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3938 - loss: 1.6845
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6867
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3921 - loss: 1.6883
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3914 - loss: 1.6897
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3906 - loss: 1.6909
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3901 - loss: 1.6919
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3895 - loss: 1.6929
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3890 - loss: 1.6938
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3886 - loss: 1.6944
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3883 - loss: 1.6948
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6952
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3875 - loss: 1.6957
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3871 - loss: 1.6962
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6965
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6966
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3863 - loss: 1.6968
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6971
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3858 - loss: 1.6974
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3856 - loss: 1.6976
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.6978
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3851 - loss: 1.6981
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6984
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6986
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3844 - loss: 1.6988
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6989
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3839 - loss: 1.6989
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3838 - loss: 1.6989
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3837 - loss: 1.6989
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6988
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6987
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6986
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6985
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6983
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6982
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3831 - loss: 1.6981
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6980
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6979 - val_accuracy: 0.3796 - val_loss: 1.7647
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.4375 - loss: 1.6817
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4204 - loss: 1.5649  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4112 - loss: 1.5711
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4037 - loss: 1.5888
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3996 - loss: 1.6035
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3987 - loss: 1.6112
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3979 - loss: 1.6182
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6242
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6290
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6326
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6356
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6373
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3972 - loss: 1.6391
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3972 - loss: 1.6405
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3972 - loss: 1.6415
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6426
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6436
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6447
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6460
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6470
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3965 - loss: 1.6479
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6487
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6494
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3958 - loss: 1.6502
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6509
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3954 - loss: 1.6514
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3952 - loss: 1.6519
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6523
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3950 - loss: 1.6526
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3949 - loss: 1.6530
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3948 - loss: 1.6532
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3947 - loss: 1.6535
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3946 - loss: 1.6537
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3945 - loss: 1.6540
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3944 - loss: 1.6541
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3943 - loss: 1.6544
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3941 - loss: 1.6546
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3940 - loss: 1.6547
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3939 - loss: 1.6550
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3937 - loss: 1.6552
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3936 - loss: 1.6553
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6556
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6558
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3933 - loss: 1.6560
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3932 - loss: 1.6562
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6564
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6564 - val_accuracy: 0.3809 - val_loss: 1.7648
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.7360
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3702 - loss: 1.6538  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3890 - loss: 1.6357
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6350
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3948 - loss: 1.6313
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3957 - loss: 1.6314
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6299
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3984 - loss: 1.6279
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3991 - loss: 1.6276
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3994 - loss: 1.6277
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3993 - loss: 1.6279
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3991 - loss: 1.6281
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3993 - loss: 1.6279
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3995 - loss: 1.6279
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3995 - loss: 1.6285
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3994 - loss: 1.6293
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3993 - loss: 1.6301
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3993 - loss: 1.6309
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3992 - loss: 1.6318
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3993 - loss: 1.6326
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3992 - loss: 1.6333
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3991 - loss: 1.6341
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3989 - loss: 1.6349
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3988 - loss: 1.6356
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3987 - loss: 1.6363
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3985 - loss: 1.6368
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3984 - loss: 1.6374
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3983 - loss: 1.6379
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3981 - loss: 1.6384
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3979 - loss: 1.6389
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3977 - loss: 1.6394
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3975 - loss: 1.6398
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3974 - loss: 1.6402
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3973 - loss: 1.6405
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6407
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6410
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6412
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6414
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6416
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6417
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3965 - loss: 1.6418
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3964 - loss: 1.6419
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3964 - loss: 1.6420
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6420
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6420
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6420 - val_accuracy: 0.3637 - val_loss: 1.7691
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.6673
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4397 - loss: 1.5739  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4223 - loss: 1.6028
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4147 - loss: 1.6158
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4111 - loss: 1.6199
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4096 - loss: 1.6229
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4083 - loss: 1.6259
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4072 - loss: 1.6296
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4065 - loss: 1.6321
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4061 - loss: 1.6328
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4059 - loss: 1.6332
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4058 - loss: 1.6339
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4058 - loss: 1.6346
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4056 - loss: 1.6352
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4053 - loss: 1.6359
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4050 - loss: 1.6362
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4048 - loss: 1.6361
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4046 - loss: 1.6363
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4043 - loss: 1.6364
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4041 - loss: 1.6364
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4039 - loss: 1.6363
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4038 - loss: 1.6361
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4036 - loss: 1.6360
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4035 - loss: 1.6358
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4035 - loss: 1.6355
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4035 - loss: 1.6352
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4035 - loss: 1.6351
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4035 - loss: 1.6350
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4035 - loss: 1.6349
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4035 - loss: 1.6349
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6348
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6348
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4033 - loss: 1.6348
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4033 - loss: 1.6348
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4033 - loss: 1.6347
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4033 - loss: 1.6347
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4033 - loss: 1.6346
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4033 - loss: 1.6346
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4033 - loss: 1.6346
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4033 - loss: 1.6346
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6346
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6346
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6346
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6346
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6346
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6346 - val_accuracy: 0.3711 - val_loss: 1.7970

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 1s/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 946us/step2025-10-31 15:38:07.907344: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:17[0m 1s/step
[1m 53/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 965us/step
[1m109/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 932us/step
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 911us/step
[1m226/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 896us/step
[1m283/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 895us/step
[1m342/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 888us/step
[1m399/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 888us/step
[1m458/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 883us/step
[1m515/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 884us/step
[1m572/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 884us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 953us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 46/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m102/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step
[1m158/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 972us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 39.52 [%]
Global F1 score (validation) = 37.01 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.21298629 0.25397557 0.23527518 ... 0.00207383 0.15948619 0.01197696]
 [0.16792542 0.25935757 0.17818485 ... 0.00439368 0.11124276 0.00462771]
 [0.20819479 0.22046012 0.22309339 ... 0.00057517 0.16947599 0.01349522]
 ...
 [0.21351938 0.3034808  0.21007983 ... 0.00050297 0.13610008 0.00576224]
 [0.19457062 0.22138138 0.20171644 ... 0.00290856 0.17067644 0.01238956]
 [0.19399767 0.27414542 0.21997078 ... 0.00259219 0.14107184 0.00840954]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 45.7 [%]
Global accuracy score (test) = 33.76 [%]
Global F1 score (train) = 43.38 [%]
Global F1 score (test) = 31.91 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.00      0.00      0.00       184
 CAMINAR CON MÓVIL O LIBRO       0.21      0.61      0.31       184
       CAMINAR USUAL SPEED       0.22      0.21      0.21       184
            CAMINAR ZIGZAG       0.57      0.44      0.50       184
          DE PIE BARRIENDO       0.29      0.31      0.30       184
   DE PIE DOBLANDO TOALLAS       0.32      0.13      0.18       184
    DE PIE MOVIENDO LIBROS       0.27      0.45      0.34       184
          DE PIE USANDO PC       0.32      0.54      0.40       184
        FASE REPOSO CON K5       0.66      0.62      0.64       184
INCREMENTAL CICLOERGOMETRO       0.63      0.52      0.57       184
           SENTADO LEYENDO       0.37      0.35      0.36       184
         SENTADO USANDO PC       0.31      0.20      0.24       184
      SENTADO VIENDO LA TV       0.28      0.28      0.28       184
   SUBIR Y BAJAR ESCALERAS       0.14      0.03      0.05       184
                    TROTAR       0.43      0.36      0.39       161

                  accuracy                           0.34      2737
                 macro avg       0.33      0.34      0.32      2737
              weighted avg       0.33      0.34      0.32      2737


Accuracy capturado en la ejecución 13: 33.76 [%]
F1-score capturado en la ejecución 13: 31.91 [%]

=== EJECUCIÓN 14 ===

--- TRAIN (ejecución 14) ---

--- TEST (ejecución 14) ---
2025-10-31 15:38:21.185098: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:38:21.196411: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761921501.209688 1687089 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761921501.213733 1687089 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761921501.224103 1687089 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921501.224124 1687089 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921501.224127 1687089 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921501.224129 1687089 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:38:21.227358: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761921503.598031 1687089 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761921506.761615 1687186 service.cc:152] XLA service 0x7dbb8c01fcf0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761921506.761658 1687186 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:38:26.825213: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761921507.245179 1687186 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761921509.890272 1687186 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:26[0m 6s/step - accuracy: 0.1250 - loss: 3.2037
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0875 - loss: 3.3378    
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0741 - loss: 3.3284
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0756 - loss: 3.3017
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0766 - loss: 3.2860
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0776 - loss: 3.2728
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0792 - loss: 3.2600
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0809 - loss: 3.2468
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0826 - loss: 3.2356
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0843 - loss: 3.2250
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0858 - loss: 3.2149
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0872 - loss: 3.2058
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0883 - loss: 3.1964
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0894 - loss: 3.1868
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0904 - loss: 3.1778
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0912 - loss: 3.1701
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0920 - loss: 3.1618
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0927 - loss: 3.1543
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0933 - loss: 3.1472
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0939 - loss: 3.1399
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0946 - loss: 3.1325
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0953 - loss: 3.1253
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0960 - loss: 3.1180
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0966 - loss: 3.1107
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0972 - loss: 3.1044
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0979 - loss: 3.0979
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0985 - loss: 3.0913
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0992 - loss: 3.0840
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0998 - loss: 3.0775
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1003 - loss: 3.0718
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1009 - loss: 3.0653
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1015 - loss: 3.0593
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1020 - loss: 3.0534
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1025 - loss: 3.0481
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1029 - loss: 3.0431
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1035 - loss: 3.0372
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1040 - loss: 3.0316
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1045 - loss: 3.0255
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1050 - loss: 3.0199
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1054 - loss: 3.0148
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1059 - loss: 3.0096
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1063 - loss: 3.0046
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1067 - loss: 2.9998
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1072 - loss: 2.9947
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1076 - loss: 2.9900
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1076 - loss: 2.9898 - val_accuracy: 0.1573 - val_loss: 2.3032
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1250 - loss: 2.3672
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1326 - loss: 2.5385  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1443 - loss: 2.5260
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1446 - loss: 2.5197
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1455 - loss: 2.5189
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1464 - loss: 2.5199
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1470 - loss: 2.5198
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1469 - loss: 2.5195
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1470 - loss: 2.5186
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1469 - loss: 2.5173
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1468 - loss: 2.5161
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1466 - loss: 2.5150
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1464 - loss: 2.5139
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1463 - loss: 2.5126
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1464 - loss: 2.5114
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1465 - loss: 2.5101
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1467 - loss: 2.5086
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1469 - loss: 2.5076
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1471 - loss: 2.5064
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1474 - loss: 2.5050
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1477 - loss: 2.5036
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5023
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1484 - loss: 2.5012
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1487 - loss: 2.5002
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1489 - loss: 2.4992
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1492 - loss: 2.4982
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1495 - loss: 2.4971
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1497 - loss: 2.4962
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1499 - loss: 2.4952
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1500 - loss: 2.4943
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1501 - loss: 2.4936
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1502 - loss: 2.4928
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1503 - loss: 2.4920
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1504 - loss: 2.4912
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1505 - loss: 2.4905
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1506 - loss: 2.4896
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1507 - loss: 2.4889
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1508 - loss: 2.4881
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1508 - loss: 2.4874
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1509 - loss: 2.4867
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1510 - loss: 2.4860
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1510 - loss: 2.4852
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1511 - loss: 2.4845
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1511 - loss: 2.4837
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1512 - loss: 2.4830
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1512 - loss: 2.4826 - val_accuracy: 0.1813 - val_loss: 2.1742
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.0000e+00 - loss: 2.6214
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1540 - loss: 2.3821      
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1649 - loss: 2.3591
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3548
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3562
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1656 - loss: 2.3577
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1658 - loss: 2.3584
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1661 - loss: 2.3596
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1663 - loss: 2.3610
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1664 - loss: 2.3617
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3611
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1671 - loss: 2.3603
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1675 - loss: 2.3594
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1677 - loss: 2.3586
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3579
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1683 - loss: 2.3572
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1686 - loss: 2.3564
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1689 - loss: 2.3554
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3545
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1694 - loss: 2.3537
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1696 - loss: 2.3529
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1698 - loss: 2.3522
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3516
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1701 - loss: 2.3511
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1702 - loss: 2.3506
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1703 - loss: 2.3503
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1705 - loss: 2.3499
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1706 - loss: 2.3495
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1706 - loss: 2.3490
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1708 - loss: 2.3485
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3480
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1710 - loss: 2.3474
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3467
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1713 - loss: 2.3461
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3454
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1716 - loss: 2.3447
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1717 - loss: 2.3442
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3437
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1719 - loss: 2.3431
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1720 - loss: 2.3425
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1722 - loss: 2.3419
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1723 - loss: 2.3413
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1724 - loss: 2.3408
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1725 - loss: 2.3403
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1726 - loss: 2.3398
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3392
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3392 - val_accuracy: 0.1970 - val_loss: 2.1062
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.8769
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1224  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2517 - loss: 2.1677
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2343 - loss: 2.1864
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2279 - loss: 2.1923
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2230 - loss: 2.1968
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.2022
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2159 - loss: 2.2069
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2132 - loss: 2.2108
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2110 - loss: 2.2146
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2090 - loss: 2.2182
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2072 - loss: 2.2224
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2054 - loss: 2.2260
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2041 - loss: 2.2284
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2030 - loss: 2.2304
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.2322
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2013 - loss: 2.2337
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2007 - loss: 2.2351
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2001 - loss: 2.2362
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1996 - loss: 2.2369
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1992 - loss: 2.2374
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1988 - loss: 2.2378
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1985 - loss: 2.2380
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1982 - loss: 2.2381
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1979 - loss: 2.2382
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1977 - loss: 2.2382
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1974 - loss: 2.2383
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1971 - loss: 2.2384
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1968 - loss: 2.2386
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1966 - loss: 2.2387
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1964 - loss: 2.2388
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1962 - loss: 2.2389
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1961 - loss: 2.2388
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1959 - loss: 2.2388
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1957 - loss: 2.2388
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1955 - loss: 2.2388
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1954 - loss: 2.2388
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1952 - loss: 2.2388
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1950 - loss: 2.2388
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1949 - loss: 2.2387
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1948 - loss: 2.2387
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1946 - loss: 2.2386
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1945 - loss: 2.2385
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1944 - loss: 2.2385
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1943 - loss: 2.2383
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1943 - loss: 2.2383 - val_accuracy: 0.2144 - val_loss: 2.0494
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.2714
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1833 - loss: 2.1591  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1833 - loss: 2.1671
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1884 - loss: 2.1668
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1914 - loss: 2.1714
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1946 - loss: 2.1732
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1955 - loss: 2.1771
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1956 - loss: 2.1806
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1959 - loss: 2.1828
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1965 - loss: 2.1852
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1965 - loss: 2.1873
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1965 - loss: 2.1894
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1968 - loss: 2.1914
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1968 - loss: 2.1934
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1968 - loss: 2.1951
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1968 - loss: 2.1961
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1967 - loss: 2.1971
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1967 - loss: 2.1978
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1967 - loss: 2.1983
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1967 - loss: 2.1990
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1966 - loss: 2.1996
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1966 - loss: 2.2001
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1965 - loss: 2.2006
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1965 - loss: 2.2009
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1964 - loss: 2.2013
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1963 - loss: 2.2015
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1962 - loss: 2.2017
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1962 - loss: 2.2019
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1962 - loss: 2.2021
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1963 - loss: 2.2023
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1963 - loss: 2.2024
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1964 - loss: 2.2025
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1964 - loss: 2.2025
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1965 - loss: 2.2026
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1966 - loss: 2.2026
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1966 - loss: 2.2025
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1967 - loss: 2.2025
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1968 - loss: 2.2023
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1968 - loss: 2.2022
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1969 - loss: 2.2021
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1969 - loss: 2.2019
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1969 - loss: 2.2018
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1970 - loss: 2.2017
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1970 - loss: 2.2015
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1970 - loss: 2.2014
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1971 - loss: 2.2013 - val_accuracy: 0.2283 - val_loss: 2.0179
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.8369
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1977 - loss: 2.1324  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2022 - loss: 2.1429
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2044 - loss: 2.1496
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2054 - loss: 2.1584
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2066 - loss: 2.1646
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2076 - loss: 2.1673
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2081 - loss: 2.1684
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2084 - loss: 2.1692
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2085 - loss: 2.1697
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2087 - loss: 2.1695
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2091 - loss: 2.1689
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2093 - loss: 2.1684
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2095 - loss: 2.1676
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.1669
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2097 - loss: 2.1663
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2098 - loss: 2.1659
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2098 - loss: 2.1652
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2099 - loss: 2.1645
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2099 - loss: 2.1640
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2100 - loss: 2.1636
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2101 - loss: 2.1633
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2102 - loss: 2.1630
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2103 - loss: 2.1625
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2105 - loss: 2.1620
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2106 - loss: 2.1616
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2108 - loss: 2.1612
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.1608
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2111 - loss: 2.1605
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1603
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1601
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2113 - loss: 2.1598
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2114 - loss: 2.1596
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2115 - loss: 2.1594
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2116 - loss: 2.1592
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2116 - loss: 2.1590
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2116 - loss: 2.1588
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2117 - loss: 2.1587
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2117 - loss: 2.1585
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2118 - loss: 2.1583
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2119 - loss: 2.1581
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2120 - loss: 2.1580
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2121 - loss: 2.1578
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2122 - loss: 2.1576
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2122 - loss: 2.1575 - val_accuracy: 0.2598 - val_loss: 1.9788
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.7464
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0139  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2455 - loss: 2.0587
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2452 - loss: 2.0707
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2457 - loss: 2.0723
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2466 - loss: 2.0763
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2461 - loss: 2.0805
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2454 - loss: 2.0843
[1m 199/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2446 - loss: 2.0880
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2435 - loss: 2.0910
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2424 - loss: 2.0936
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2417 - loss: 2.0949
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2411 - loss: 2.0963
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2405 - loss: 2.0981
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2402 - loss: 2.0993
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2399 - loss: 2.1001
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2397 - loss: 2.1007
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2394 - loss: 2.1012
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2393 - loss: 2.1015
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2391 - loss: 2.1016
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2389 - loss: 2.1016
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2386 - loss: 2.1016
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2384 - loss: 2.1016
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.1016
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2380 - loss: 2.1015
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2378 - loss: 2.1014
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2376 - loss: 2.1013
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2375 - loss: 2.1012
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1012
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1013
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2370 - loss: 2.1013
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2368 - loss: 2.1014
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2367 - loss: 2.1014
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2365 - loss: 2.1014
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2364 - loss: 2.1014
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2362 - loss: 2.1015
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2361 - loss: 2.1015
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2360 - loss: 2.1015
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2359 - loss: 2.1015
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2359 - loss: 2.1015
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2358 - loss: 2.1015
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2358 - loss: 2.1015
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2358 - loss: 2.1015
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2358 - loss: 2.1014
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2358 - loss: 2.1013
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2358 - loss: 2.1013
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2358 - loss: 2.1013 - val_accuracy: 0.2490 - val_loss: 1.9628
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0048
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2428 - loss: 2.0934  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2455 - loss: 2.0902
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2458 - loss: 2.0865
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2448 - loss: 2.0881
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2449 - loss: 2.0876
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2446 - loss: 2.0885
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2448 - loss: 2.0876
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.0872
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2453 - loss: 2.0866
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2455 - loss: 2.0866
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2456 - loss: 2.0871
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2455 - loss: 2.0873
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2456 - loss: 2.0874
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2458 - loss: 2.0871
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.0867
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2462 - loss: 2.0861
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2464 - loss: 2.0853
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2466 - loss: 2.0845
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2467 - loss: 2.0838
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2468 - loss: 2.0832
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.0825
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2471 - loss: 2.0820
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2473 - loss: 2.0816
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2475 - loss: 2.0811
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2477 - loss: 2.0805
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2479 - loss: 2.0799
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2482 - loss: 2.0791
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.0785
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.0778
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2490 - loss: 2.0770
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2493 - loss: 2.0764
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2496 - loss: 2.0756
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2500 - loss: 2.0748
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2503 - loss: 2.0740
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0733
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2508 - loss: 2.0726
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2510 - loss: 2.0719
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.0712
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2514 - loss: 2.0706
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2517 - loss: 2.0699
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2519 - loss: 2.0693
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2521 - loss: 2.0688
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2523 - loss: 2.0682
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2525 - loss: 2.0677
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2527 - loss: 2.0672
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2528 - loss: 2.0669 - val_accuracy: 0.2788 - val_loss: 1.9356
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.5812
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3143 - loss: 1.9511  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3005 - loss: 1.9656
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2967 - loss: 1.9630
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9618
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9608
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9584
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 1.9566
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 1.9555
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 1.9558
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 1.9568
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 1.9578
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 1.9587
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 1.9597
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 1.9610
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 1.9622
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2929 - loss: 1.9634
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9647
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9660
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2920 - loss: 1.9672
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2918 - loss: 1.9681
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2916 - loss: 1.9691
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 1.9701
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2912 - loss: 1.9712
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9722
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2907 - loss: 1.9734
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2904 - loss: 1.9745
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2901 - loss: 1.9756
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2898 - loss: 1.9765
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2895 - loss: 1.9775
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2892 - loss: 1.9784
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2889 - loss: 1.9793
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2886 - loss: 1.9801
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2884 - loss: 1.9808
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2882 - loss: 1.9816
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2880 - loss: 1.9823
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 1.9829
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 1.9835
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 1.9840
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2874 - loss: 1.9845
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2873 - loss: 1.9849
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2872 - loss: 1.9854
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2871 - loss: 1.9857
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2870 - loss: 1.9861
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2870 - loss: 1.9862 - val_accuracy: 0.2903 - val_loss: 1.9148
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.6142
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2918 - loss: 1.8908  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2881 - loss: 1.9124
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2871 - loss: 1.9172
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2866 - loss: 1.9257
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 1.9360
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 1.9434
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2855 - loss: 1.9481
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 1.9503
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 1.9518
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2878 - loss: 1.9528
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 1.9534
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2890 - loss: 1.9536
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2895 - loss: 1.9537
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2898 - loss: 1.9536
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2903 - loss: 1.9535
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2907 - loss: 1.9533
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9532
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 1.9529
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2919 - loss: 1.9524
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9522
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9521
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2929 - loss: 1.9521
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2931 - loss: 1.9522
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 1.9523
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 1.9525
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9526
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 1.9528
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 1.9529
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 1.9530
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9532
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9534
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2948 - loss: 1.9536
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 1.9537
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 1.9539
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9540
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9541
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9542
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9543
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9544
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9545
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 1.9545
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 1.9545
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9545
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9545
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9545 - val_accuracy: 0.2853 - val_loss: 1.8979
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.1875 - loss: 2.0231
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2872 - loss: 1.9194  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2909 - loss: 1.9114
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9067
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2969 - loss: 1.9020
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2987 - loss: 1.8992
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2994 - loss: 1.8980
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 1.8980
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 1.8992
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9018
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 1.9040
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9057
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 1.9076
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9089
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9101
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9110
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 1.9119
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 1.9129
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 1.9137
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 1.9144
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 1.9150
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 1.9156
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 1.9161
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 1.9167
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9172
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9178
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9182
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 1.9185
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 1.9188
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9191
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9192
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9194
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9195
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9195
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9196
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9197
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9197
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9197
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 1.9197
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9196
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9196
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9195
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9194
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9193
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9192
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9192 - val_accuracy: 0.3008 - val_loss: 1.8977
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9013
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3277 - loss: 1.9362  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3196 - loss: 1.9337
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3205 - loss: 1.9250
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3219 - loss: 1.9161
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3227 - loss: 1.9098
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3225 - loss: 1.9079
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 1.9074
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3206 - loss: 1.9081
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 1.9077
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 1.9072
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 1.9064
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 1.9056
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 1.9045
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 1.9033
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 1.9021
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 1.9009
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3198 - loss: 1.9002
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 1.8994
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8989
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 1.8986
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8982
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8979
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8976
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8971
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8968
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8965
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8963
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8961
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8959
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8956
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8953
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8950
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3192 - loss: 1.8947
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3192 - loss: 1.8944
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8941
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8938
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 1.8936
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 1.8933
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 1.8931
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 1.8929
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 1.8927
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8924
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8920
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3204 - loss: 1.8918 - val_accuracy: 0.3591 - val_loss: 1.8269
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0423
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2801 - loss: 1.8776  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2928 - loss: 1.8709
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2982 - loss: 1.8688
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3023 - loss: 1.8689
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 1.8709
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 1.8716
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 1.8699
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 1.8684
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 1.8672
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 1.8665
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3160 - loss: 1.8653
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8641
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3186 - loss: 1.8622
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 1.8607
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8596
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3208 - loss: 1.8586
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3213 - loss: 1.8575
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 1.8568
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 1.8560
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3228 - loss: 1.8550
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3232 - loss: 1.8542
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3236 - loss: 1.8535
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8529
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8524
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 1.8519
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 1.8514
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 1.8510
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 1.8506
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 1.8501
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8497
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 1.8493
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3270 - loss: 1.8491
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3272 - loss: 1.8489
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 1.8488
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 1.8487
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3279 - loss: 1.8486
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3281 - loss: 1.8485
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3283 - loss: 1.8484
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3285 - loss: 1.8483
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3287 - loss: 1.8483
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8482
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3290 - loss: 1.8481
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3292 - loss: 1.8481
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3293 - loss: 1.8480 - val_accuracy: 0.3406 - val_loss: 1.8453
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3398
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2831 - loss: 2.0052  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2903 - loss: 1.9323
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3019 - loss: 1.8977
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3069 - loss: 1.8827
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3108 - loss: 1.8733
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 1.8660
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8604
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8552
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 1.8502
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3234 - loss: 1.8461
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 1.8428
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 1.8400
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3276 - loss: 1.8379
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 1.8359
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 1.8347
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8336
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8326
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8317
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8309
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3328 - loss: 1.8301
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 1.8293
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8289
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8285
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8282
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8279
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8276
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3349 - loss: 1.8274
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3351 - loss: 1.8271
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8269
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8269
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3356 - loss: 1.8268
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8267
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3358 - loss: 1.8267
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8267
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8267
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8266
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8265
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8265
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8265
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8264
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3368 - loss: 1.8263
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3369 - loss: 1.8261
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8260
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8258
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8257 - val_accuracy: 0.3882 - val_loss: 1.7901
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.0636
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2883 - loss: 1.8156  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3143 - loss: 1.7807
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3290 - loss: 1.7722
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3382 - loss: 1.7678
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3428 - loss: 1.7698
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3446 - loss: 1.7731
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7747
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.7752
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7759
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7766
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7769
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3487 - loss: 1.7775
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7783
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7794
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7801
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7808
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7814
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7817
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7821
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7825
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7827
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7828
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7832
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7836
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7839
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7842
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7844
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7846
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7849
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7851
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3500 - loss: 1.7854
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7857
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7860
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7862
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7863
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7864
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7866
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7868
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7870
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7873
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7875
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7877
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7879
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7881
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7882 - val_accuracy: 0.3623 - val_loss: 1.7912
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.7507
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.3191 - loss: 1.8142  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3192 - loss: 1.8064
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3234 - loss: 1.7868
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3290 - loss: 1.7734
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3320 - loss: 1.7672
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3336 - loss: 1.7647
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3350 - loss: 1.7632
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3358 - loss: 1.7630
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3360 - loss: 1.7630
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3360 - loss: 1.7633
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3360 - loss: 1.7638
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3362 - loss: 1.7644
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3365 - loss: 1.7649
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.7655
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.7662
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.7670
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.7675
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3368 - loss: 1.7681
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3371 - loss: 1.7685
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3375 - loss: 1.7688
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3378 - loss: 1.7690
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3381 - loss: 1.7693
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.7695
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3386 - loss: 1.7697
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3389 - loss: 1.7699
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.7701
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.7703
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.7704
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.7704
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.7702
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.7701
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3406 - loss: 1.7699
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3409 - loss: 1.7697
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7695
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3414 - loss: 1.7694
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.7692
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.7691
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3421 - loss: 1.7690
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3423 - loss: 1.7689
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.7688
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.7686
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3431 - loss: 1.7685
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.7684
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3435 - loss: 1.7683
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3435 - loss: 1.7683 - val_accuracy: 0.3689 - val_loss: 1.7874
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.6146
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8140  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3184 - loss: 1.8420
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8319
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3217 - loss: 1.8169
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8052
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3299 - loss: 1.7966
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 1.7912
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3358 - loss: 1.7857
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.7814
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3394 - loss: 1.7783
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3408 - loss: 1.7761
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3421 - loss: 1.7745
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 1.7732
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3443 - loss: 1.7719
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3453 - loss: 1.7708
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3464 - loss: 1.7696
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.7687
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3481 - loss: 1.7678
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3487 - loss: 1.7671
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7663
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.7655
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3506 - loss: 1.7647
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7638
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7629
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7621
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7616
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3530 - loss: 1.7611
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7606
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7601
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3540 - loss: 1.7597
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7592
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7587
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7583
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3553 - loss: 1.7579
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3555 - loss: 1.7577
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3557 - loss: 1.7574
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3559 - loss: 1.7573
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7572
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7570
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7569
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7567
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7566
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7564
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7562
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7562 - val_accuracy: 0.3685 - val_loss: 1.7826
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0983
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7699  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7363
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7143
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3701 - loss: 1.7097
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7084
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7093
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7099
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7105
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7102
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7103
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7106
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7115
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3773 - loss: 1.7123
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7127
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7134
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3773 - loss: 1.7144
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7153
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7158
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7162
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7167
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3770 - loss: 1.7171
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7173
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7173
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7175
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7177
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3768 - loss: 1.7179
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7181
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.7184
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.7186
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7189
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7192
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.7194
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7197
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7198
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3762 - loss: 1.7200
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3761 - loss: 1.7201
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3760 - loss: 1.7203
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7205
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3758 - loss: 1.7207
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3757 - loss: 1.7209
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3756 - loss: 1.7210
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.7212
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.7214
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7216
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7217 - val_accuracy: 0.3606 - val_loss: 1.7636
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.5880
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4063 - loss: 1.6898  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4044 - loss: 1.6886
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4019 - loss: 1.6851
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3988 - loss: 1.6848
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3962 - loss: 1.6856
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3931 - loss: 1.6863
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6875
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3889 - loss: 1.6889
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3874 - loss: 1.6896
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6900
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3857 - loss: 1.6903
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3852 - loss: 1.6904
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6903
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6900
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6900
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3839 - loss: 1.6904
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6910
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6914
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6917
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3828 - loss: 1.6919
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3827 - loss: 1.6919
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3827 - loss: 1.6917
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6915
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6914
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6912
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3824 - loss: 1.6911
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3823 - loss: 1.6909
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6909
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6908
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3821 - loss: 1.6907
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3821 - loss: 1.6907
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3821 - loss: 1.6907
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3821 - loss: 1.6907
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3820 - loss: 1.6909
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3820 - loss: 1.6910
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6911
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6913
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6914
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3817 - loss: 1.6916
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3816 - loss: 1.6919
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3815 - loss: 1.6921
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3814 - loss: 1.6924
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3813 - loss: 1.6927
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3812 - loss: 1.6930
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3812 - loss: 1.6930 - val_accuracy: 0.3722 - val_loss: 1.7898
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2500 - loss: 1.5562
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4039 - loss: 1.6760  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3855 - loss: 1.7208
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3859 - loss: 1.7158
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3872 - loss: 1.7081
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3869 - loss: 1.7031
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6998
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3866 - loss: 1.6987
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3864 - loss: 1.6969
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3862 - loss: 1.6956
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6946
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6939
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3861 - loss: 1.6932
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3862 - loss: 1.6930
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3863 - loss: 1.6927
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3864 - loss: 1.6926
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3866 - loss: 1.6922
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6919
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3868 - loss: 1.6916
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6916
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6916
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3868 - loss: 1.6917
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6916
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6915
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6913
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6910
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6907
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6905
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6904
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6904
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3868 - loss: 1.6906
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3868 - loss: 1.6907
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6909
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3866 - loss: 1.6911
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6913
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6915
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6915
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6916
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6916
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3864 - loss: 1.6917
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3864 - loss: 1.6918
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3864 - loss: 1.6919
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6920
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6921
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6922
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6923
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6923 - val_accuracy: 0.3660 - val_loss: 1.7631
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.5000 - loss: 1.4433
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3897 - loss: 1.6817  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6840
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3814 - loss: 1.6854
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3809 - loss: 1.6859
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6843
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3823 - loss: 1.6786
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3844 - loss: 1.6730
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3857 - loss: 1.6698
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3866 - loss: 1.6678
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3875 - loss: 1.6656
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3882 - loss: 1.6635
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3888 - loss: 1.6616
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3892 - loss: 1.6603
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3897 - loss: 1.6591
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3899 - loss: 1.6585
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3902 - loss: 1.6583
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3904 - loss: 1.6582
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3905 - loss: 1.6583
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3906 - loss: 1.6585
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6586
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6588
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3908 - loss: 1.6589
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6589
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6589
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6589
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6588
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3910 - loss: 1.6588
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3910 - loss: 1.6588
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6587
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6587
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6587
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6587
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3908 - loss: 1.6588
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3908 - loss: 1.6588
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3908 - loss: 1.6589
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3908 - loss: 1.6589
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3908 - loss: 1.6589
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6590
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6590
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6591
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3906 - loss: 1.6591
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3906 - loss: 1.6592
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3906 - loss: 1.6593
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3906 - loss: 1.6593
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3905 - loss: 1.6593
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3905 - loss: 1.6593 - val_accuracy: 0.3815 - val_loss: 1.7834

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 1s/step
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 994us/step2025-10-31 15:39:34.312808: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:39[0m 1s/step
[1m 53/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 974us/step
[1m111/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 915us/step
[1m169/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 906us/step
[1m223/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 911us/step
[1m278/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 913us/step
[1m333/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 913us/step
[1m394/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 900us/step
[1m453/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 893us/step
[1m510/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 893us/step
[1m564/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 897us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 974us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 51/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m109/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 928us/step
[1m156/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 970us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 37.11 [%]
Global F1 score (validation) = 35.86 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.23005056 0.2975139  0.20030828 ... 0.00178724 0.12711549 0.01736715]
 [0.22340792 0.19696957 0.23373674 ... 0.00083233 0.19035806 0.01165075]
 [0.24090356 0.26765645 0.22833166 ... 0.00100724 0.14761354 0.01194168]
 ...
 [0.2576783  0.25245005 0.23374514 ... 0.0010218  0.16362262 0.01879535]
 [0.26261497 0.25830573 0.20778853 ... 0.00045802 0.18077919 0.04417995]
 [0.1439649  0.20688958 0.13744602 ... 0.00985923 0.08098035 0.01311955]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 48.8 [%]
Global accuracy score (test) = 35.44 [%]
Global F1 score (train) = 47.42 [%]
Global F1 score (test) = 33.8 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.23      0.20      0.21       184
 CAMINAR CON MÓVIL O LIBRO       0.20      0.33      0.25       184
       CAMINAR USUAL SPEED       0.24      0.17      0.20       184
            CAMINAR ZIGZAG       0.46      0.62      0.53       184
          DE PIE BARRIENDO       0.29      0.38      0.33       184
   DE PIE DOBLANDO TOALLAS       0.34      0.38      0.36       184
    DE PIE MOVIENDO LIBROS       0.33      0.38      0.36       184
          DE PIE USANDO PC       0.30      0.61      0.40       184
        FASE REPOSO CON K5       0.84      0.64      0.72       184
INCREMENTAL CICLOERGOMETRO       0.70      0.49      0.58       184
           SENTADO LEYENDO       0.29      0.51      0.37       184
         SENTADO USANDO PC       0.57      0.07      0.13       184
      SENTADO VIENDO LA TV       0.15      0.03      0.05       184
   SUBIR Y BAJAR ESCALERAS       0.32      0.11      0.17       184
                    TROTAR       0.42      0.40      0.41       161

                  accuracy                           0.35      2737
                 macro avg       0.38      0.35      0.34      2737
              weighted avg       0.38      0.35      0.34      2737


Accuracy capturado en la ejecución 14: 35.44 [%]
F1-score capturado en la ejecución 14: 33.8 [%]

=== EJECUCIÓN 15 ===

--- TRAIN (ejecución 15) ---

--- TEST (ejecución 15) ---
2025-10-31 15:39:47.527928: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:39:47.539342: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761921587.552875 1690574 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761921587.557188 1690574 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761921587.567134 1690574 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921587.567152 1690574 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921587.567154 1690574 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921587.567156 1690574 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:39:47.570392: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761921589.922984 1690574 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761921592.999762 1690688 service.cc:152] XLA service 0x76e594003140 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761921592.999834 1690688 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:39:53.065429: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761921593.483335 1690688 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761921596.120183 1690688 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45:57[0m 5s/step - accuracy: 0.0625 - loss: 3.3689
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.0757 - loss: 3.4176    
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0715 - loss: 3.4076
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0697 - loss: 3.4124
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0692 - loss: 3.3980
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0690 - loss: 3.3828
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0696 - loss: 3.3699
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0710 - loss: 3.3556
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0726 - loss: 3.3411
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0740 - loss: 3.3267
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0755 - loss: 3.3111
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0768 - loss: 3.2969
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0781 - loss: 3.2826
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0794 - loss: 3.2692
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0806 - loss: 3.2569
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0818 - loss: 3.2441
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0828 - loss: 3.2327
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0839 - loss: 3.2210
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0848 - loss: 3.2108
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0857 - loss: 3.2011
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0865 - loss: 3.1912
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0873 - loss: 3.1817
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0881 - loss: 3.1729
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0888 - loss: 3.1643
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0895 - loss: 3.1559
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0901 - loss: 3.1482
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0908 - loss: 3.1400
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0914 - loss: 3.1324
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0920 - loss: 3.1255
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0926 - loss: 3.1184
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0930 - loss: 3.1121
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0936 - loss: 3.1052
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0941 - loss: 3.0982
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0947 - loss: 3.0919
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0952 - loss: 3.0856
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0957 - loss: 3.0795
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0962 - loss: 3.0736
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0967 - loss: 3.0677
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0972 - loss: 3.0620
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0977 - loss: 3.0563
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0981 - loss: 3.0508
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0986 - loss: 3.0461
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0990 - loss: 3.0410
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0995 - loss: 3.0356
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.0998 - loss: 3.0333
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.0998 - loss: 3.0331 - val_accuracy: 0.1813 - val_loss: 2.2902
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.1250 - loss: 2.4122
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1485 - loss: 2.4523  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1433 - loss: 2.5019
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1434 - loss: 2.5104
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1440 - loss: 2.5160
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1441 - loss: 2.5197
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1435 - loss: 2.5229
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1428 - loss: 2.5247
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1422 - loss: 2.5259
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1416 - loss: 2.5272
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1414 - loss: 2.5282
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1414 - loss: 2.5287
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1414 - loss: 2.5290
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1415 - loss: 2.5288
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1418 - loss: 2.5281
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1421 - loss: 2.5271
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1424 - loss: 2.5262
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1427 - loss: 2.5253
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1429 - loss: 2.5243
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1431 - loss: 2.5233
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1434 - loss: 2.5223
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1437 - loss: 2.5212
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1439 - loss: 2.5202
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1442 - loss: 2.5190
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1444 - loss: 2.5178
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1446 - loss: 2.5167
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1447 - loss: 2.5154
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1449 - loss: 2.5142
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1450 - loss: 2.5129
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1451 - loss: 2.5116
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1453 - loss: 2.5103
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1454 - loss: 2.5091
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1456 - loss: 2.5078
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1457 - loss: 2.5065
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1459 - loss: 2.5053
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.5041
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1461 - loss: 2.5029
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1463 - loss: 2.5017
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1464 - loss: 2.5007
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1466 - loss: 2.4997
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1467 - loss: 2.4986
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1468 - loss: 2.4975
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1469 - loss: 2.4966
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1471 - loss: 2.4955
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1472 - loss: 2.4945
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1472 - loss: 2.4942 - val_accuracy: 0.1959 - val_loss: 2.1932
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.4345
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1312 - loss: 2.4783  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1416 - loss: 2.4609
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1487 - loss: 2.4440
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1510 - loss: 2.4346
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1526 - loss: 2.4263
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1530 - loss: 2.4201
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1530 - loss: 2.4164
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1528 - loss: 2.4142
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1532 - loss: 2.4104
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1539 - loss: 2.4067
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1545 - loss: 2.4033
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1552 - loss: 2.4001
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1558 - loss: 2.3971
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1563 - loss: 2.3947
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1568 - loss: 2.3924
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1572 - loss: 2.3905
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1575 - loss: 2.3885
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1579 - loss: 2.3864
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1582 - loss: 2.3843
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1586 - loss: 2.3826
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1589 - loss: 2.3807
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1593 - loss: 2.3790
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1595 - loss: 2.3775
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1597 - loss: 2.3761
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1600 - loss: 2.3747
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1602 - loss: 2.3735
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1604 - loss: 2.3726
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1606 - loss: 2.3714
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1607 - loss: 2.3705
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1609 - loss: 2.3696
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1611 - loss: 2.3686
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1612 - loss: 2.3676
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1614 - loss: 2.3666
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1616 - loss: 2.3657
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1618 - loss: 2.3647
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1619 - loss: 2.3639
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1621 - loss: 2.3631
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1622 - loss: 2.3623
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1624 - loss: 2.3615
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1625 - loss: 2.3608
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1626 - loss: 2.3602
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1627 - loss: 2.3596
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1629 - loss: 2.3590
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1630 - loss: 2.3583 - val_accuracy: 0.2009 - val_loss: 2.1155
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2801
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1590 - loss: 2.2701  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1661 - loss: 2.2779
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1648 - loss: 2.2857
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1638 - loss: 2.2918
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1634 - loss: 2.2944
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1633 - loss: 2.2946
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1636 - loss: 2.2953
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1642 - loss: 2.2965
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1649 - loss: 2.2974
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1657 - loss: 2.2971
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1663 - loss: 2.2968
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1670 - loss: 2.2961
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1677 - loss: 2.2953
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1684 - loss: 2.2942
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1690 - loss: 2.2931
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1696 - loss: 2.2921
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1703 - loss: 2.2908
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1709 - loss: 2.2897
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1715 - loss: 2.2886
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1720 - loss: 2.2875
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1725 - loss: 2.2864
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1730 - loss: 2.2855
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.2846
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1739 - loss: 2.2837
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1743 - loss: 2.2829
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1746 - loss: 2.2822
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1750 - loss: 2.2815
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1753 - loss: 2.2809
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1757 - loss: 2.2803
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2796
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1763 - loss: 2.2790
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1766 - loss: 2.2785
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1769 - loss: 2.2779
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1771 - loss: 2.2774
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1773 - loss: 2.2770
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1776 - loss: 2.2764
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1778 - loss: 2.2760
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.2755
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1783 - loss: 2.2749
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1785 - loss: 2.2744
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1788 - loss: 2.2739
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1790 - loss: 2.2733
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.2729
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.2724
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1796 - loss: 2.2721 - val_accuracy: 0.2057 - val_loss: 2.0854
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.1384
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1971 - loss: 2.1724  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1962 - loss: 2.1898
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1957 - loss: 2.1989
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1967 - loss: 2.1986
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1972 - loss: 2.1979
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1979 - loss: 2.1980
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1983 - loss: 2.1985
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1985 - loss: 2.1989
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1985 - loss: 2.1994
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1988 - loss: 2.1994
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1990 - loss: 2.1990
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1989 - loss: 2.1988
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1986 - loss: 2.1988
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1983 - loss: 2.1989
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1981 - loss: 2.1989
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1978 - loss: 2.1988
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1976 - loss: 2.1986
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1975 - loss: 2.1983
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1976 - loss: 2.1977
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1976 - loss: 2.1974
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1976 - loss: 2.1970
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1977 - loss: 2.1968
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1978 - loss: 2.1965
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1979 - loss: 2.1963
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1980 - loss: 2.1962
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1982 - loss: 2.1960
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.1958
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1985 - loss: 2.1956
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1986 - loss: 2.1954
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1988 - loss: 2.1952
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1989 - loss: 2.1949
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1990 - loss: 2.1946
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1991 - loss: 2.1943
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1992 - loss: 2.1940
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1994 - loss: 2.1937
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1995 - loss: 2.1935
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1996 - loss: 2.1933
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1997 - loss: 2.1932
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1998 - loss: 2.1930
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1999 - loss: 2.1929
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2000 - loss: 2.1928
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2001 - loss: 2.1926
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2002 - loss: 2.1924
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2003 - loss: 2.1923 - val_accuracy: 0.2407 - val_loss: 2.0160
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.7969
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2623 - loss: 2.0807  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2418 - loss: 2.0973
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2286 - loss: 2.1077
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2246 - loss: 2.1101
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1137
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2223 - loss: 2.1193
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2219 - loss: 2.1226
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2218 - loss: 2.1253
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2217 - loss: 2.1279
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2215 - loss: 2.1301
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2214 - loss: 2.1318
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.1330
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2209 - loss: 2.1344
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2205 - loss: 2.1359
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2203 - loss: 2.1369
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.1376
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.1381
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.1384
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.1386
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.1388
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.1389
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.1389
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2202 - loss: 2.1390
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2203 - loss: 2.1390
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2203 - loss: 2.1390
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2204 - loss: 2.1391
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2204 - loss: 2.1392
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2205 - loss: 2.1392
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2206 - loss: 2.1392
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2208 - loss: 2.1391
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.1390
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2210 - loss: 2.1388
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2211 - loss: 2.1386
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2213 - loss: 2.1384
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2214 - loss: 2.1382
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2215 - loss: 2.1379
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2216 - loss: 2.1377
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2217 - loss: 2.1375
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2218 - loss: 2.1372
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2220 - loss: 2.1369
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2221 - loss: 2.1366
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2222 - loss: 2.1363
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.1360
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2224 - loss: 2.1357
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2225 - loss: 2.1357 - val_accuracy: 0.3045 - val_loss: 1.9513
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.7778
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3247 - loss: 1.9785  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2876 - loss: 2.0248
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2773 - loss: 2.0365
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2690 - loss: 2.0412
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2640 - loss: 2.0450
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2609 - loss: 2.0485
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2590 - loss: 2.0517
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2578 - loss: 2.0536
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2568 - loss: 2.0549
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2559 - loss: 2.0559
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2552 - loss: 2.0564
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.0575
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2536 - loss: 2.0588
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2528 - loss: 2.0602
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2522 - loss: 2.0615
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2518 - loss: 2.0626
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2515 - loss: 2.0637
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.0645
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2512 - loss: 2.0651
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2509 - loss: 2.0658
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.0665
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0672
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.0678
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.0683
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2497 - loss: 2.0688
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2495 - loss: 2.0691
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2494 - loss: 2.0694
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.0697
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2491 - loss: 2.0700
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2489 - loss: 2.0703
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2488 - loss: 2.0706
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2488 - loss: 2.0708
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.0709
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2486 - loss: 2.0711
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2486 - loss: 2.0712
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2486 - loss: 2.0712
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.0713
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.0714
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.0714
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.0715
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2484 - loss: 2.0715
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2484 - loss: 2.0716
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2484 - loss: 2.0717
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2484 - loss: 2.0717 - val_accuracy: 0.3173 - val_loss: 1.9167
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1081
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2721 - loss: 2.0114  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2788 - loss: 2.0168
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2758 - loss: 2.0258
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2745 - loss: 2.0261
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2739 - loss: 2.0254
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2735 - loss: 2.0254
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2730 - loss: 2.0251
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.0246
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0240
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2718 - loss: 2.0230
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0222
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.0215
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.0206
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.0202
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0199
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0198
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2707 - loss: 2.0196
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.0194
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.0193
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.0191
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.0189
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.0186
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.0185
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.0185
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0185
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0185
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0184
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.0184
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.0184
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0184
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0183
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0182
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0181
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0181
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2712 - loss: 2.0180
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0180
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0179
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2714 - loss: 2.0178
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2714 - loss: 2.0178
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0178
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2716 - loss: 2.0178
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2716 - loss: 2.0178
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0178
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0177
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0177 - val_accuracy: 0.3526 - val_loss: 1.8458
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.6921
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2632 - loss: 1.9070  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2663 - loss: 1.9325
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2670 - loss: 1.9406
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2681 - loss: 1.9482
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2685 - loss: 1.9552
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2687 - loss: 1.9617
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2692 - loss: 1.9648
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 1.9657
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 1.9657
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 1.9653
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2735 - loss: 1.9650
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2740 - loss: 1.9656
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2746 - loss: 1.9656
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2751 - loss: 1.9657
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 1.9660
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2762 - loss: 1.9661
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 1.9660
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2773 - loss: 1.9658
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 1.9658
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 1.9659
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 1.9662
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2792 - loss: 1.9666
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 1.9671
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 1.9674
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 1.9677
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 1.9680
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2810 - loss: 1.9682
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2813 - loss: 1.9683
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2816 - loss: 1.9683
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 1.9684
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9685
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 1.9686
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 1.9687
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 1.9688
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 1.9690
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9692
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 1.9693
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9694
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 1.9696
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 1.9697
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 1.9697
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 1.9698
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 1.9698
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2841 - loss: 1.9699
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2842 - loss: 1.9699 - val_accuracy: 0.2792 - val_loss: 1.9466
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.0625 - loss: 1.8648
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2510 - loss: 1.9915  
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2645 - loss: 1.9865
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 1.9778
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9696
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 1.9639
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2874 - loss: 1.9589
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2878 - loss: 1.9566
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 1.9559
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 1.9553
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2893 - loss: 1.9550
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2896 - loss: 1.9547
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2899 - loss: 1.9540
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2902 - loss: 1.9532
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2906 - loss: 1.9523
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2909 - loss: 1.9514
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2912 - loss: 1.9507
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 1.9501
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9494
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2921 - loss: 1.9486
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 1.9479
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9473
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2928 - loss: 1.9469
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2930 - loss: 1.9465
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 1.9461
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2933 - loss: 1.9458
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2934 - loss: 1.9454
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9451
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9447
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 1.9443
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 1.9439
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 1.9436
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 1.9432
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9429
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2948 - loss: 1.9425
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 1.9422
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9418
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9415
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9412
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2957 - loss: 1.9410
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 1.9407
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9403
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9400
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9398
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9395
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9395 - val_accuracy: 0.3430 - val_loss: 1.8168
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.1749
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2781 - loss: 2.0321  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2941 - loss: 1.9783
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9555
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2988 - loss: 1.9396
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2991 - loss: 1.9334
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 1.9284
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 1.9227
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 1.9184
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3025 - loss: 1.9158
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 1.9145
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3025 - loss: 1.9134
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3025 - loss: 1.9123
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 1.9108
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 1.9094
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3032 - loss: 1.9082
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3033 - loss: 1.9073
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3034 - loss: 1.9067
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 1.9064
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9060
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 1.9056
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9052
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 1.9048
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 1.9045
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 1.9042
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 1.9040
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 1.9037
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3049 - loss: 1.9033
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9029
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9025
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9021
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9018
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 1.9014
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 1.9010
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.9007
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9003
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 1.8999
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 1.8995
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 1.8992
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 1.8988
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3073 - loss: 1.8985
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 1.8982
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3076 - loss: 1.8980
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3078 - loss: 1.8978
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3078 - loss: 1.8977 - val_accuracy: 0.3702 - val_loss: 1.8005
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3750 - loss: 1.9258
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3602 - loss: 1.8771  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3477 - loss: 1.8813
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8991
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3293 - loss: 1.9061
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3278 - loss: 1.9069
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 1.9083
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3255 - loss: 1.9092
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 1.9086
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 1.9076
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 1.9060
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3239 - loss: 1.9047
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 1.9034
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 1.9019
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 1.9006
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 1.8990
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 1.8975
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8961
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 1.8950
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 1.8939
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8926
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8916
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8907
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8900
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8894
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8887
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8880
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8874
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8867
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8861
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8856
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8850
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8844
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8838
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8834
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8831
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8828
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8826
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8824
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8822
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8820
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8818
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8816
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8814
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8812
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8811 - val_accuracy: 0.3798 - val_loss: 1.7637
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9432
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3271 - loss: 1.8654  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8447
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3408 - loss: 1.8342
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3434 - loss: 1.8241
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3448 - loss: 1.8213
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3459 - loss: 1.8181
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3475 - loss: 1.8143
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8124
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8124
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3487 - loss: 1.8128
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3481 - loss: 1.8140
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3471 - loss: 1.8159
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 1.8170
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3457 - loss: 1.8177
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3452 - loss: 1.8183
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3447 - loss: 1.8190
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3442 - loss: 1.8198
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 1.8206
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 1.8215
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8225
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3424 - loss: 1.8232
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3420 - loss: 1.8239
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8246
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8252
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3409 - loss: 1.8259
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8265
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8270
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8275
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8279
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8282
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8285
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8287
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8288
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3386 - loss: 1.8289
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8290
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8291
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8291
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8292
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8292
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8292
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8293
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3378 - loss: 1.8292
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3378 - loss: 1.8292
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8291
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8291
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8291 - val_accuracy: 0.3863 - val_loss: 1.7461
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9267
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7244  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7327
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7354
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7430
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7509
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7550
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7576
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7604
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7631
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7647
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7661
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7676
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7695
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3551 - loss: 1.7713
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7732
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7751
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3531 - loss: 1.7771
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3525 - loss: 1.7788
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3521 - loss: 1.7802
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3517 - loss: 1.7813
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3514 - loss: 1.7822
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3511 - loss: 1.7832
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3509 - loss: 1.7841
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3506 - loss: 1.7848
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3503 - loss: 1.7855
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3501 - loss: 1.7861
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3500 - loss: 1.7867
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7874
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7880
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7885
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7889
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7894
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7899
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3491 - loss: 1.7905
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3490 - loss: 1.7911
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3489 - loss: 1.7917
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3487 - loss: 1.7922
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3486 - loss: 1.7927
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7931
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3484 - loss: 1.7936
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3484 - loss: 1.7940
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3483 - loss: 1.7944
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3483 - loss: 1.7948
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7951
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7951 - val_accuracy: 0.3782 - val_loss: 1.7346
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.6535
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4261 - loss: 1.7020  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4024 - loss: 1.7258
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3906 - loss: 1.7390
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3864 - loss: 1.7419
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3831 - loss: 1.7426
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3809 - loss: 1.7414
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3793 - loss: 1.7418
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3777 - loss: 1.7448
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3764 - loss: 1.7473
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7494
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7511
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7529
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7545
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7556
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7565
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3704 - loss: 1.7575
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7587
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7595
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7606
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7614
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7622
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7628
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7634
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7641
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7647
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7652
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7656
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7661
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7664
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7666
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7667
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7668
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7668
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7668
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7668
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7669
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7669
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7670
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7670
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7671
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7672
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7673
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7673
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7674
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7675 - val_accuracy: 0.3425 - val_loss: 1.7509
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.4667
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3409 - loss: 1.8161  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3452 - loss: 1.8082
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3477 - loss: 1.8031
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3490 - loss: 1.7965
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3509 - loss: 1.7915
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7873
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3541 - loss: 1.7846
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7835
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7823
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7813
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7801
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7791
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7779
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7767
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7756
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7746
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7738
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7729
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7723
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7716
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7710
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7704
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7699
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7695
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7693
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7692
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7691
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7689
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7688
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7686
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7683
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7682
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7679
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7677
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7674
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7671
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7669
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7667
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7664
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7662
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7659
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7657
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7654
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7652
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7651 - val_accuracy: 0.3880 - val_loss: 1.7231
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1297
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3468 - loss: 1.7649  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7582
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7572
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7600
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7618
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7625
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7637
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7648
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7647
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7640
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7634
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7625
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7613
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7599
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7586
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7574
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7562
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7548
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7534
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7522
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7511
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7499
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7487
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7477
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7467
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7459
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7451
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3672 - loss: 1.7445
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7439
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7433
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7428
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3677 - loss: 1.7424
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7420
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7416
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3680 - loss: 1.7411
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7407
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7403
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7400
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7397
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7394
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7391
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3687 - loss: 1.7389
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7386
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7383
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7382 - val_accuracy: 0.3771 - val_loss: 1.7288
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.4192
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3879 - loss: 1.7403  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3821 - loss: 1.7264
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3760 - loss: 1.7252
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7205
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3761 - loss: 1.7153
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7130
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7118
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.7107
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.7095
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3789 - loss: 1.7083
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3789 - loss: 1.7073
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3787 - loss: 1.7069
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.7070
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.7067
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7067
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.7069
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3779 - loss: 1.7068
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3778 - loss: 1.7067
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3779 - loss: 1.7067
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.7065
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.7064
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.7064
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7061
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7058
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7054
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7052
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7050
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7047
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7045
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7045
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7044
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7042
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7040
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7039
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7038
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7038
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7037
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7037
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7036
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7036
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7036
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7036
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7036
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7036
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7036
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7036 - val_accuracy: 0.3530 - val_loss: 1.7553
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.5681
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3393 - loss: 1.7817  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7548
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3617 - loss: 1.7328
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7252
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7206
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7145
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3762 - loss: 1.7104
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.7085
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3798 - loss: 1.7073
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3812 - loss: 1.7060
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3825 - loss: 1.7048
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3835 - loss: 1.7035
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3843 - loss: 1.7028
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3848 - loss: 1.7027
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3851 - loss: 1.7026
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3855 - loss: 1.7022
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3857 - loss: 1.7021
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3858 - loss: 1.7020
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3859 - loss: 1.7021
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3861 - loss: 1.7020
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3862 - loss: 1.7020
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3863 - loss: 1.7020
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3863 - loss: 1.7019
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3863 - loss: 1.7018
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3863 - loss: 1.7016
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3864 - loss: 1.7014
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3864 - loss: 1.7011
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3864 - loss: 1.7008
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.7004
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.7000
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3866 - loss: 1.6996
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3868 - loss: 1.6992
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6989
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6986
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6984
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3871 - loss: 1.6981
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3872 - loss: 1.6979
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3873 - loss: 1.6977
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3873 - loss: 1.6975
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3873 - loss: 1.6974
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3874 - loss: 1.6972
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3874 - loss: 1.6971
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3874 - loss: 1.6969
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3874 - loss: 1.6968 - val_accuracy: 0.3804 - val_loss: 1.7370
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.6875 - loss: 1.1274
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4592 - loss: 1.6078  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4312 - loss: 1.6354
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4212 - loss: 1.6524
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4154 - loss: 1.6558
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4137 - loss: 1.6545
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4121 - loss: 1.6541
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4106 - loss: 1.6546
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4094 - loss: 1.6557
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4083 - loss: 1.6559
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4071 - loss: 1.6559
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4063 - loss: 1.6564
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4056 - loss: 1.6568
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4048 - loss: 1.6578
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4042 - loss: 1.6592
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4037 - loss: 1.6605
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6611
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4032 - loss: 1.6616
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4031 - loss: 1.6620
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4030 - loss: 1.6623
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4029 - loss: 1.6626
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4028 - loss: 1.6627
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4027 - loss: 1.6627
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4026 - loss: 1.6627
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4025 - loss: 1.6627
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4024 - loss: 1.6627
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4022 - loss: 1.6627
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4021 - loss: 1.6626
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4019 - loss: 1.6625
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4018 - loss: 1.6624
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4017 - loss: 1.6622
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4016 - loss: 1.6621
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4016 - loss: 1.6621
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4015 - loss: 1.6620
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4014 - loss: 1.6621
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4013 - loss: 1.6621
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4013 - loss: 1.6620
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4012 - loss: 1.6620
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4012 - loss: 1.6619
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6618
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6617
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6617
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6616
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6615
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6614
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6613 - val_accuracy: 0.3870 - val_loss: 1.7710
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7046
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4355 - loss: 1.7059  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4217 - loss: 1.6695
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4215 - loss: 1.6566
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4218 - loss: 1.6512
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4214 - loss: 1.6473
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4201 - loss: 1.6447
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4183 - loss: 1.6434
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4163 - loss: 1.6439
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4145 - loss: 1.6448
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4129 - loss: 1.6456
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4117 - loss: 1.6465
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4107 - loss: 1.6473
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4095 - loss: 1.6484
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4086 - loss: 1.6495
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4078 - loss: 1.6503
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4071 - loss: 1.6511
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4064 - loss: 1.6518
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4058 - loss: 1.6524
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4053 - loss: 1.6531
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4048 - loss: 1.6538
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4042 - loss: 1.6546
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4036 - loss: 1.6551
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4032 - loss: 1.6556
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4029 - loss: 1.6559
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4026 - loss: 1.6564
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4022 - loss: 1.6569
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4019 - loss: 1.6574
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4016 - loss: 1.6576
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4014 - loss: 1.6580
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6582
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4008 - loss: 1.6584
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4006 - loss: 1.6586
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4004 - loss: 1.6588
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4002 - loss: 1.6591
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4000 - loss: 1.6593
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3997 - loss: 1.6597
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3995 - loss: 1.6600
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3994 - loss: 1.6602
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3992 - loss: 1.6605
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3991 - loss: 1.6606
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3989 - loss: 1.6608
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3988 - loss: 1.6609
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3986 - loss: 1.6610
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3985 - loss: 1.6611
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3984 - loss: 1.6612
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3984 - loss: 1.6612 - val_accuracy: 0.3759 - val_loss: 1.7438

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:33[0m 1s/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:41:00.374212: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:14[0m 1s/step
[1m 53/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 983us/step
[1m107/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 961us/step
[1m158/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 970us/step
[1m211/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 966us/step
[1m264/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 963us/step
[1m323/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 944us/step
[1m378/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 940us/step
[1m430/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 945us/step
[1m487/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 939us/step
[1m542/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 937us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 50/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m108/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 943us/step
[1m164/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 926us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 38.15 [%]
Global F1 score (validation) = 35.01 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.24907945 0.25431526 0.18461533 ... 0.00452649 0.16011563 0.01222386]
 [0.16065036 0.2249388  0.11764767 ... 0.00926023 0.07801717 0.00609038]
 [0.252049   0.26571262 0.18237838 ... 0.0033107  0.17264237 0.01324895]
 ...
 [0.23994127 0.26091886 0.18056813 ... 0.00514036 0.14847375 0.01121798]
 [0.23246211 0.16705453 0.20366175 ... 0.00054459 0.19063699 0.01198533]
 [0.23485367 0.2656444  0.17254682 ... 0.00634999 0.14164682 0.0118321 ]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 47.71 [%]
Global accuracy score (test) = 33.98 [%]
Global F1 score (train) = 45.34 [%]
Global F1 score (test) = 31.67 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.17      0.29      0.22       184
 CAMINAR CON MÓVIL O LIBRO       0.25      0.52      0.33       184
       CAMINAR USUAL SPEED       0.00      0.00      0.00       184
            CAMINAR ZIGZAG       0.53      0.47      0.50       184
          DE PIE BARRIENDO       0.32      0.39      0.35       184
   DE PIE DOBLANDO TOALLAS       0.24      0.10      0.14       184
    DE PIE MOVIENDO LIBROS       0.36      0.55      0.43       184
          DE PIE USANDO PC       0.35      0.59      0.44       184
        FASE REPOSO CON K5       1.00      0.58      0.74       184
INCREMENTAL CICLOERGOMETRO       0.65      0.51      0.57       184
           SENTADO LEYENDO       0.03      0.01      0.02       184
         SENTADO USANDO PC       0.32      0.24      0.28       184
      SENTADO VIENDO LA TV       0.26      0.43      0.32       184
   SUBIR Y BAJAR ESCALERAS       0.12      0.03      0.04       184
                    TROTAR       0.35      0.39      0.37       161

                  accuracy                           0.34      2737
                 macro avg       0.33      0.34      0.32      2737
              weighted avg       0.33      0.34      0.32      2737


Accuracy capturado en la ejecución 15: 33.98 [%]
F1-score capturado en la ejecución 15: 31.67 [%]

=== EJECUCIÓN 16 ===

--- TRAIN (ejecución 16) ---

--- TEST (ejecución 16) ---
2025-10-31 15:41:13.513297: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:41:13.525283: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761921673.539247 1694033 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761921673.543421 1694033 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761921673.554445 1694033 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921673.554471 1694033 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921673.554473 1694033 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921673.554475 1694033 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:41:13.557814: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761921675.964389 1694033 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761921679.036856 1694162 service.cc:152] XLA service 0x72ddd0014640 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761921679.037245 1694162 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:41:19.103300: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761921679.524588 1694162 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761921682.172185 1694162 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45:57[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.5945
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0727 - loss: 3.3065        
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0708 - loss: 3.2929
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0725 - loss: 3.2745
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0751 - loss: 3.2574
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0774 - loss: 3.2437
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0796 - loss: 3.2292
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0810 - loss: 3.2172
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0823 - loss: 3.2060
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0833 - loss: 3.1950
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0841 - loss: 3.1841
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0848 - loss: 3.1732
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0855 - loss: 3.1633
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0863 - loss: 3.1536
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0873 - loss: 3.1437
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0881 - loss: 3.1339
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0891 - loss: 3.1236
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0898 - loss: 3.1146
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0906 - loss: 3.1058
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0913 - loss: 3.0980
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0919 - loss: 3.0903
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0925 - loss: 3.0830
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0931 - loss: 3.0763
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0937 - loss: 3.0690
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0943 - loss: 3.0621
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0948 - loss: 3.0557
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0954 - loss: 3.0498
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0960 - loss: 3.0433
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0966 - loss: 3.0373
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0971 - loss: 3.0314
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0976 - loss: 3.0254
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0981 - loss: 3.0199
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0986 - loss: 3.0143
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0990 - loss: 3.0093
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0995 - loss: 3.0040
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0999 - loss: 2.9992
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1004 - loss: 2.9942
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1008 - loss: 2.9892
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1012 - loss: 2.9846
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1016 - loss: 2.9799
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1019 - loss: 2.9754
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1023 - loss: 2.9710
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1027 - loss: 2.9667
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1030 - loss: 2.9630
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1030 - loss: 2.9628 - val_accuracy: 0.1678 - val_loss: 2.3266
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.0625 - loss: 2.5534
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1182 - loss: 2.5691  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1249 - loss: 2.5562
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1311 - loss: 2.5338
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1356 - loss: 2.5211
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1384 - loss: 2.5155
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1398 - loss: 2.5126
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1407 - loss: 2.5111
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1416 - loss: 2.5092
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1425 - loss: 2.5076
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1435 - loss: 2.5065
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1444 - loss: 2.5053
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1449 - loss: 2.5044
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1454 - loss: 2.5033
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1457 - loss: 2.5024
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1459 - loss: 2.5016
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1461 - loss: 2.5009
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1462 - loss: 2.5001
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1464 - loss: 2.4992
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1466 - loss: 2.4984
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1467 - loss: 2.4977
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1468 - loss: 2.4972
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1468 - loss: 2.4966
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1468 - loss: 2.4961
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1469 - loss: 2.4954
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1469 - loss: 2.4947
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1469 - loss: 2.4940
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1469 - loss: 2.4933
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1470 - loss: 2.4925
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1471 - loss: 2.4917
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1472 - loss: 2.4910
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1473 - loss: 2.4902
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1475 - loss: 2.4895
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1476 - loss: 2.4888
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1477 - loss: 2.4880
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1478 - loss: 2.4874
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1479 - loss: 2.4867
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1480 - loss: 2.4860
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1481 - loss: 2.4854
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1482 - loss: 2.4846
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1483 - loss: 2.4839
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1484 - loss: 2.4832
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1486 - loss: 2.4825
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1487 - loss: 2.4817
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1488 - loss: 2.4810 - val_accuracy: 0.1883 - val_loss: 2.2164
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.5053
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1174 - loss: 2.5296  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1266 - loss: 2.5024
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1329 - loss: 2.4762
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1366 - loss: 2.4583
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1390 - loss: 2.4452
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1409 - loss: 2.4378
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1422 - loss: 2.4320
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1433 - loss: 2.4270
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1445 - loss: 2.4226
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1456 - loss: 2.4187
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1467 - loss: 2.4155
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1475 - loss: 2.4131
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1481 - loss: 2.4113
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1487 - loss: 2.4096
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1493 - loss: 2.4085
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1498 - loss: 2.4072
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1503 - loss: 2.4058
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1508 - loss: 2.4046
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1513 - loss: 2.4031
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1517 - loss: 2.4018
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1522 - loss: 2.4004
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1527 - loss: 2.3991
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1531 - loss: 2.3980
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1536 - loss: 2.3968
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1539 - loss: 2.3958
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1543 - loss: 2.3948
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1545 - loss: 2.3939
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1548 - loss: 2.3930
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1551 - loss: 2.3920
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.3911
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1557 - loss: 2.3903
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1559 - loss: 2.3896
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1561 - loss: 2.3889
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1564 - loss: 2.3882
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1566 - loss: 2.3875
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1569 - loss: 2.3868
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1571 - loss: 2.3860
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1573 - loss: 2.3854
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1575 - loss: 2.3847
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1577 - loss: 2.3839
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1580 - loss: 2.3831
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1581 - loss: 2.3824
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1583 - loss: 2.3817
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1584 - loss: 2.3812 - val_accuracy: 0.2022 - val_loss: 2.1476
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2482
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1904 - loss: 2.3030  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1776 - loss: 2.3181
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1762 - loss: 2.3154
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1761 - loss: 2.3074
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1759 - loss: 2.3017
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1755 - loss: 2.2981
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1751 - loss: 2.2956
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1754 - loss: 2.2930
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1756 - loss: 2.2916
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1756 - loss: 2.2905
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1756 - loss: 2.2894
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1757 - loss: 2.2885
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1758 - loss: 2.2878
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2871
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1762 - loss: 2.2866
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1764 - loss: 2.2863
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1768 - loss: 2.2859
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.2856
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.2852
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1776 - loss: 2.2849
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.2847
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.2846
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1782 - loss: 2.2845
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.2843
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1786 - loss: 2.2841
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1788 - loss: 2.2840
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1790 - loss: 2.2840
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1791 - loss: 2.2839
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.2837
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.2834
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.2832
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.2830
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1799 - loss: 2.2827
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1801 - loss: 2.2824
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.2821
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.2818
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1805 - loss: 2.2815
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1807 - loss: 2.2811
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1808 - loss: 2.2808
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1810 - loss: 2.2805
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1811 - loss: 2.2802
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1812 - loss: 2.2798
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1814 - loss: 2.2795
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1814 - loss: 2.2795 - val_accuracy: 0.2111 - val_loss: 2.1008
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3305
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1670 - loss: 2.2360  
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1742 - loss: 2.2282
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1772 - loss: 2.2257
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1796 - loss: 2.2218
[1m 141/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1797 - loss: 2.2199
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1796 - loss: 2.2203
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1792 - loss: 2.2232
[1m 219/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1790 - loss: 2.2254
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1790 - loss: 2.2268
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1793 - loss: 2.2271
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1796 - loss: 2.2272
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1799 - loss: 2.2274
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1802 - loss: 2.2276
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1803 - loss: 2.2281
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1805 - loss: 2.2285
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1807 - loss: 2.2287
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1809 - loss: 2.2288
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1811 - loss: 2.2289
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1813 - loss: 2.2289
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1815 - loss: 2.2291
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1816 - loss: 2.2294
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1818 - loss: 2.2299
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1820 - loss: 2.2302
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1822 - loss: 2.2305
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2309
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1826 - loss: 2.2313
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.2315
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1830 - loss: 2.2317
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.2318
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2319
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2319
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1838 - loss: 2.2319
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1840 - loss: 2.2318
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1842 - loss: 2.2317
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2315
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2312
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2309
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2306
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2303
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2299
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.2295
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2292
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1865 - loss: 2.2288
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1866 - loss: 2.2287 - val_accuracy: 0.2790 - val_loss: 2.0257
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.2158
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2195 - loss: 2.2781  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2265 - loss: 2.2345
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2236 - loss: 2.2207
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2199 - loss: 2.2122
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2178 - loss: 2.2072
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2165 - loss: 2.2038
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2159 - loss: 2.2004
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2156 - loss: 2.1962
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2154 - loss: 2.1928
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2152 - loss: 2.1902
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2149 - loss: 2.1879
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2148 - loss: 2.1862
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.1849
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2145 - loss: 2.1841
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2143 - loss: 2.1832
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2141 - loss: 2.1823
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2139 - loss: 2.1816
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2137 - loss: 2.1810
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2137 - loss: 2.1803
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2137 - loss: 2.1795
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2137 - loss: 2.1788
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2137 - loss: 2.1783
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2137 - loss: 2.1777
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2136 - loss: 2.1773
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2135 - loss: 2.1768
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2135 - loss: 2.1763
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2136 - loss: 2.1757
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2137 - loss: 2.1751
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2138 - loss: 2.1744
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2139 - loss: 2.1738
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2140 - loss: 2.1732
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2142 - loss: 2.1725
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2143 - loss: 2.1719
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2145 - loss: 2.1713
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2146 - loss: 2.1707
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2148 - loss: 2.1701
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2149 - loss: 2.1695
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2151 - loss: 2.1691
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2152 - loss: 2.1686
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2153 - loss: 2.1681
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2155 - loss: 2.1676
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2156 - loss: 2.1672
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2158 - loss: 2.1667
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2159 - loss: 2.1664 - val_accuracy: 0.2912 - val_loss: 1.9713
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 1.8353
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1930 - loss: 2.1469  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2091 - loss: 2.1383
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2213 - loss: 2.1245
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2285 - loss: 2.1113
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2328 - loss: 2.1019
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2354 - loss: 2.0981
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2375 - loss: 2.0955
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2394 - loss: 2.0929
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.0918
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2415 - loss: 2.0916
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.0920
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2423 - loss: 2.0927
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.0935
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.0944
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.0949
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.0953
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.0956
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2430 - loss: 2.0956
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2430 - loss: 2.0957
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2431 - loss: 2.0958
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.0957
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2433 - loss: 2.0957
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2433 - loss: 2.0958
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.0958
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.0957
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.0956
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.0953
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.0951
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.0948
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.0945
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.0941
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2437 - loss: 2.0937
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2438 - loss: 2.0934
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2440 - loss: 2.0930
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2441 - loss: 2.0928
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2442 - loss: 2.0926
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2442 - loss: 2.0924
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2443 - loss: 2.0923
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2444 - loss: 2.0922
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2445 - loss: 2.0921
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2446 - loss: 2.0919
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2447 - loss: 2.0917
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2448 - loss: 2.0915
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2448 - loss: 2.0914
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2448 - loss: 2.0914 - val_accuracy: 0.3068 - val_loss: 1.8950
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2944
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1985 - loss: 2.1885  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2145 - loss: 2.1433
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2266 - loss: 2.1168
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2321 - loss: 2.1070
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2366 - loss: 2.0978
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2405 - loss: 2.0894
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2436 - loss: 2.0828
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2463 - loss: 2.0762
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.0701
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2501 - loss: 2.0659
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2515 - loss: 2.0616
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2528 - loss: 2.0577
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.0545
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2548 - loss: 2.0518
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2555 - loss: 2.0497
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2561 - loss: 2.0477
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2565 - loss: 2.0463
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2569 - loss: 2.0451
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2572 - loss: 2.0442
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2575 - loss: 2.0434
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2578 - loss: 2.0427
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2580 - loss: 2.0420
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2583 - loss: 2.0415
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2585 - loss: 2.0409
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.0403
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.0396
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 2.0390
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.0387
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.0383
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2596 - loss: 2.0381
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.0379
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.0377
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.0375
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.0373
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.0371
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.0370
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2606 - loss: 2.0369
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2607 - loss: 2.0367
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.0366
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2609 - loss: 2.0364
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2610 - loss: 2.0362
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2611 - loss: 2.0360
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2612 - loss: 2.0358
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2613 - loss: 2.0357 - val_accuracy: 0.3164 - val_loss: 1.8798
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.2500 - loss: 2.0491
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2872 - loss: 2.0110  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2840 - loss: 2.0135
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2834 - loss: 2.0141
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.0115
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 2.0090
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2781 - loss: 2.0075
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2773 - loss: 2.0067
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 2.0068
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.0061
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.0046
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2777 - loss: 2.0026
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 2.0009
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 1.9994
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2787 - loss: 1.9979
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 1.9967
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 1.9953
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 1.9941
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 1.9931
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 1.9922
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 1.9917
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 1.9911
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2811 - loss: 1.9907
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 1.9905
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 1.9903
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2813 - loss: 1.9902
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9900
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2815 - loss: 1.9897
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2816 - loss: 1.9896
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 1.9895
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 1.9895
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 1.9895
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 1.9896
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2820 - loss: 1.9897
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9897
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9898
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 1.9897
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 1.9897
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 1.9896
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 1.9895
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2826 - loss: 1.9895
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 1.9894
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 1.9894
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9893
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9892
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9892 - val_accuracy: 0.3532 - val_loss: 1.8103
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.8500
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2799 - loss: 1.9444  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2816 - loss: 1.9708
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2831 - loss: 1.9716
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2851 - loss: 1.9703
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2876 - loss: 1.9661
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2901 - loss: 1.9616
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2911 - loss: 1.9593
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9573
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9550
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9530
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 1.9514
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9504
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2944 - loss: 1.9493
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2948 - loss: 1.9484
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9477
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2957 - loss: 1.9468
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9458
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9450
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2966 - loss: 1.9441
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 1.9432
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9423
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 1.9416
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9408
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 1.9401
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9396
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9391
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 1.9386
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9382
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9379
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9376
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9372
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9370
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9368
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9367
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2988 - loss: 1.9366
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 1.9365
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 1.9364
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 1.9363
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 1.9362
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 1.9360
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 1.9359
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2992 - loss: 1.9357
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9356 - val_accuracy: 0.3397 - val_loss: 1.8313
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.9383
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9220  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9001
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3045 - loss: 1.9021
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3063 - loss: 1.8976
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3077 - loss: 1.8961
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 1.8949
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 1.8942
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 1.8936
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 1.8926
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 1.8920
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 1.8913
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 1.8909
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 1.8908
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 1.8909
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 1.8909
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3160 - loss: 1.8905
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 1.8899
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3167 - loss: 1.8893
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8890
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8886
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8884
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8884
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8883
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3172 - loss: 1.8883
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8881
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8881
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8880
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 1.8879
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8878
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8877
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8876
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8876
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 1.8876
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8876
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8876
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8876
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3184 - loss: 1.8875
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3184 - loss: 1.8875
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8875
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8875
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8875
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8875
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8876
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8876 - val_accuracy: 0.3473 - val_loss: 1.7990
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1250 - loss: 2.3910
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9014  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3100 - loss: 1.8865
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8818
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3176 - loss: 1.8804
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8807
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8795
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3167 - loss: 1.8785
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8767
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8754
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3176 - loss: 1.8745
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8742
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8738
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8733
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8728
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8720
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3181 - loss: 1.8712
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8704
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8695
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8688
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8683
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8678
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8674
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8670
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 1.8666
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 1.8661
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8656
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 1.8650
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 1.8645
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8641
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8638
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8635
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8632
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8630
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8629
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8628
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8628
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8627
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8627
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8627
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8626
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8626
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8625
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8625
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8624 - val_accuracy: 0.3578 - val_loss: 1.7860
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2537
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3639 - loss: 1.8376  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3607 - loss: 1.8309
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3597 - loss: 1.8193
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3566 - loss: 1.8167
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3545 - loss: 1.8146
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3529 - loss: 1.8129
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3516 - loss: 1.8131
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3502 - loss: 1.8140
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.8155
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.8168
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.8179
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3457 - loss: 1.8195
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3452 - loss: 1.8211
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3447 - loss: 1.8224
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3443 - loss: 1.8232
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3440 - loss: 1.8240
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 1.8244
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3436 - loss: 1.8245
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3435 - loss: 1.8248
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3434 - loss: 1.8252
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.8254
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 1.8255
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3431 - loss: 1.8256
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3430 - loss: 1.8255
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3430 - loss: 1.8254
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3430 - loss: 1.8254
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3430 - loss: 1.8253
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.8253
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.8253
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8254
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8255
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8257
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3424 - loss: 1.8260
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3423 - loss: 1.8262
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3421 - loss: 1.8264
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3420 - loss: 1.8266
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8268
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8269
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8270
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8271
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8273
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8274
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8275
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8276 - val_accuracy: 0.3702 - val_loss: 1.7702
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.5495
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3829 - loss: 1.6891  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3759 - loss: 1.6978
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7041
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7132
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7229
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7330
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7417
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7485
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7541
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3514 - loss: 1.7589
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3503 - loss: 1.7631
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7664
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7697
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7726
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3468 - loss: 1.7749
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3462 - loss: 1.7770
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7787
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7803
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3450 - loss: 1.7814
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3447 - loss: 1.7824
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3446 - loss: 1.7832
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3445 - loss: 1.7839
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3443 - loss: 1.7845
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3442 - loss: 1.7851
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3441 - loss: 1.7858
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3439 - loss: 1.7864
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3438 - loss: 1.7869
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3437 - loss: 1.7874
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3435 - loss: 1.7879
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3434 - loss: 1.7884
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3432 - loss: 1.7889
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3431 - loss: 1.7893
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3430 - loss: 1.7896
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.7900
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.7903
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.7905
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3426 - loss: 1.7909
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.7912
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3424 - loss: 1.7915
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3423 - loss: 1.7917
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3422 - loss: 1.7919
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3422 - loss: 1.7921
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3422 - loss: 1.7922
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3422 - loss: 1.7923 - val_accuracy: 0.3599 - val_loss: 1.7789
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.5051
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4067 - loss: 1.7683  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3907 - loss: 1.7770
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3801 - loss: 1.7779
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7845
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7897
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7914
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7901
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7889
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7870
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7851
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7842
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7833
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7822
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7816
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7810
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7807
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7805
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7804
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3559 - loss: 1.7802
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7803
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7805
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7809
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7812
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7815
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7819
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3530 - loss: 1.7823
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3527 - loss: 1.7827
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7831
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7834
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.7838
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3514 - loss: 1.7841
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7843
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7845
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3508 - loss: 1.7847
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3507 - loss: 1.7848
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3506 - loss: 1.7848
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3505 - loss: 1.7849
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3504 - loss: 1.7849
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3503 - loss: 1.7849
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3503 - loss: 1.7849
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7848
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7847
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7846
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7845 - val_accuracy: 0.3660 - val_loss: 1.7585
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.5625 - loss: 1.4745
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4307 - loss: 1.6362  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4137 - loss: 1.6666
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4004 - loss: 1.6838
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3924 - loss: 1.6971
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3863 - loss: 1.7094
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3822 - loss: 1.7189
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3792 - loss: 1.7251
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7287
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3760 - loss: 1.7322
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3748 - loss: 1.7346
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3737 - loss: 1.7365
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7378
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7392
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7403
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7413
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7422
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7428
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7432
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7434
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3687 - loss: 1.7437
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7441
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7445
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3677 - loss: 1.7448
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7451
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7454
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7456
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7458
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7459
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7460
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7460
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7461
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7462
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7462
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7463
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7464
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7465
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7465
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7467
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7469
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7470
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7471
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7472
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7472
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7474 - val_accuracy: 0.3608 - val_loss: 1.7793
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.4754
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7368  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7488
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7607
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7632
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3556 - loss: 1.7596
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7564
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7526
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7505
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7488
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7474
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3617 - loss: 1.7463
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7449
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7434
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7416
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7404
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7394
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7385
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7373
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7364
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7356
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7350
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7342
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7336
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7331
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7327
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7325
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7323
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7321
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7320
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7319
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7318
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7316
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7315
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3662 - loss: 1.7314
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7313
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7313
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7313
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7312
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7312
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7311
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7310
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7310
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7309
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7308
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7307 - val_accuracy: 0.3743 - val_loss: 1.7622
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.4664
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7056  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3484 - loss: 1.7379
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7426
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3458 - loss: 1.7406
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 1.7384
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7349
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7317
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3501 - loss: 1.7301
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7292
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7289
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3528 - loss: 1.7291
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7291
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7292
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7289
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7285
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7281
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7279
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7278
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7279
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7279
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7281
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7284
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7287
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7288
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7288
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7288
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7286
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7285
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7283
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7281
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7279
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7276
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7274
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7270
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7267
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7264
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7260
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7257
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7252
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7249
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7245
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7242
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7239
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7237 - val_accuracy: 0.3458 - val_loss: 1.8643
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8342
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3597 - loss: 1.6618  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3627 - loss: 1.6781
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3632 - loss: 1.6911
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3658 - loss: 1.6938
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3681 - loss: 1.6959
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.6952
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3740 - loss: 1.6936
[1m 222/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3754 - loss: 1.6936
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3758 - loss: 1.6940
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3763 - loss: 1.6941
[1m 302/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3768 - loss: 1.6942
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6939
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.6934
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3787 - loss: 1.6929
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3792 - loss: 1.6925
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3797 - loss: 1.6923
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3801 - loss: 1.6919
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3806 - loss: 1.6915
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6910
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3814 - loss: 1.6905
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3818 - loss: 1.6901
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6894
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6888
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3828 - loss: 1.6883
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3829 - loss: 1.6879
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3831 - loss: 1.6876
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3831 - loss: 1.6873
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6870
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6867
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6865
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6863
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6860
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6859
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3831 - loss: 1.6858
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3831 - loss: 1.6857
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6857
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6857
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6857
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6857
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6857
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6857
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6856
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6856
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6856 - val_accuracy: 0.3778 - val_loss: 1.7997
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.6711
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3878 - loss: 1.6602  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6491
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3823 - loss: 1.6518
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3804 - loss: 1.6575
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3802 - loss: 1.6619
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3803 - loss: 1.6635
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3796 - loss: 1.6652
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3792 - loss: 1.6662
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3790 - loss: 1.6672
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3787 - loss: 1.6682
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.6688
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3782 - loss: 1.6692
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.6694
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6699
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.6702
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3773 - loss: 1.6707
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6713
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.6720
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3768 - loss: 1.6728
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3767 - loss: 1.6734
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6740
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6744
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6746
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.6749
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.6752
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.6754
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6756
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6757
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6759
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6762
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.6764
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.6765
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.6767
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.6770
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.6773
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.6775
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.6778
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.6779
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.6781
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.6782
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.6783
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.6783
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6784
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6784 - val_accuracy: 0.3758 - val_loss: 1.7829

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 1s/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 983us/step2025-10-31 15:42:22.876961: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:06[0m 1s/step
[1m 46/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m 96/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m155/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 981us/step
[1m210/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 964us/step
[1m264/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 957us/step
[1m326/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 933us/step
[1m381/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 930us/step
[1m430/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 941us/step
[1m481/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 946us/step
[1m534/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 947us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 941us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 938us/step
[1m115/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 886us/step
[1m165/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 923us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 37.59 [%]
Global F1 score (validation) = 36.0 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.1778011  0.14046179 0.18550126 ... 0.00537238 0.19102621 0.02192821]
 [0.11054296 0.11271209 0.09337395 ... 0.01491903 0.0757901  0.01022564]
 [0.07075849 0.06614548 0.0622285  ... 0.06976964 0.08262821 0.22465089]
 ...
 [0.18655589 0.170418   0.18141802 ... 0.00476134 0.16807929 0.00804965]
 [0.15132083 0.18183261 0.13845682 ... 0.00631629 0.08880999 0.00350251]
 [0.21921377 0.24978897 0.24071649 ... 0.0022043  0.17565733 0.01183832]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.34 [%]
Global accuracy score (test) = 32.85 [%]
Global F1 score (train) = 44.45 [%]
Global F1 score (test) = 31.12 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.17      0.08      0.10       184
 CAMINAR CON MÓVIL O LIBRO       0.29      0.43      0.34       184
       CAMINAR USUAL SPEED       0.22      0.21      0.22       184
            CAMINAR ZIGZAG       0.52      0.57      0.54       184
          DE PIE BARRIENDO       0.28      0.26      0.27       184
   DE PIE DOBLANDO TOALLAS       0.16      0.03      0.05       184
    DE PIE MOVIENDO LIBROS       0.28      0.53      0.37       184
          DE PIE USANDO PC       0.36      0.52      0.42       184
        FASE REPOSO CON K5       0.66      0.58      0.62       184
INCREMENTAL CICLOERGOMETRO       0.75      0.57      0.65       184
           SENTADO LEYENDO       0.20      0.38      0.26       184
         SENTADO USANDO PC       0.08      0.05      0.06       184
      SENTADO VIENDO LA TV       0.19      0.11      0.14       184
   SUBIR Y BAJAR ESCALERAS       0.28      0.19      0.23       184
                    TROTAR       0.37      0.45      0.40       161

                  accuracy                           0.33      2737
                 macro avg       0.32      0.33      0.31      2737
              weighted avg       0.32      0.33      0.31      2737


Accuracy capturado en la ejecución 16: 32.85 [%]
F1-score capturado en la ejecución 16: 31.12 [%]

=== EJECUCIÓN 17 ===

--- TRAIN (ejecución 17) ---

--- TEST (ejecución 17) ---
2025-10-31 15:42:36.039308: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:42:36.050544: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761921756.063621 1697347 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761921756.067827 1697347 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761921756.077564 1697347 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921756.077584 1697347 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921756.077586 1697347 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921756.077587 1697347 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:42:36.080836: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761921758.446103 1697347 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761921761.567481 1697471 service.cc:152] XLA service 0x7a807401b530 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761921761.567568 1697471 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:42:41.640718: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761921762.072048 1697471 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761921764.683631 1697471 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46:15[0m 5s/step - accuracy: 0.0000e+00 - loss: 2.9556
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0424 - loss: 3.4525        
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0530 - loss: 3.4628
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0559 - loss: 3.4516
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0582 - loss: 3.4341
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0620 - loss: 3.4116
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0649 - loss: 3.3894
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0674 - loss: 3.3673
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0693 - loss: 3.3470
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0705 - loss: 3.3309
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0718 - loss: 3.3133
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0731 - loss: 3.2957
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0745 - loss: 3.2798
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0756 - loss: 3.2666
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0767 - loss: 3.2526
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0778 - loss: 3.2397
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0785 - loss: 3.2295
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0793 - loss: 3.2189
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0801 - loss: 3.2080
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0810 - loss: 3.1979
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0819 - loss: 3.1874
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0827 - loss: 3.1785
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0835 - loss: 3.1690
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0843 - loss: 3.1603
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0851 - loss: 3.1517
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0859 - loss: 3.1432
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0866 - loss: 3.1348
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0873 - loss: 3.1267
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0880 - loss: 3.1186
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0887 - loss: 3.1110
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0894 - loss: 3.1039
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0900 - loss: 3.0970
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0906 - loss: 3.0907
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0912 - loss: 3.0843
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0918 - loss: 3.0774
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0923 - loss: 3.0715
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0929 - loss: 3.0651
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0935 - loss: 3.0589
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0940 - loss: 3.0531
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0946 - loss: 3.0475
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0951 - loss: 3.0416
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0956 - loss: 3.0358
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0961 - loss: 3.0306
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0965 - loss: 3.0256
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.0969 - loss: 3.0212
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.0969 - loss: 3.0210 - val_accuracy: 0.1499 - val_loss: 2.3070
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.2500 - loss: 2.7224
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1514 - loss: 2.5548  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1483 - loss: 2.5257
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1456 - loss: 2.5240
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1439 - loss: 2.5274
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1423 - loss: 2.5282
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1412 - loss: 2.5287
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1407 - loss: 2.5303
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1401 - loss: 2.5309
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1396 - loss: 2.5307
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1394 - loss: 2.5300
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1394 - loss: 2.5288
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1395 - loss: 2.5272
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1397 - loss: 2.5255
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1399 - loss: 2.5242
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1403 - loss: 2.5228
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1407 - loss: 2.5211
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1412 - loss: 2.5194
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1415 - loss: 2.5182
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1418 - loss: 2.5168
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1421 - loss: 2.5152
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1424 - loss: 2.5139
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1428 - loss: 2.5126
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1431 - loss: 2.5113
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1434 - loss: 2.5101
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1438 - loss: 2.5086
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1442 - loss: 2.5072
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1445 - loss: 2.5057
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1448 - loss: 2.5043
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1452 - loss: 2.5030
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1456 - loss: 2.5016
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1459 - loss: 2.5001
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1462 - loss: 2.4988
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1465 - loss: 2.4976
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1468 - loss: 2.4964
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1471 - loss: 2.4952
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1474 - loss: 2.4940
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1477 - loss: 2.4928
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1480 - loss: 2.4916
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1482 - loss: 2.4906
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1484 - loss: 2.4895
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1486 - loss: 2.4885
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1489 - loss: 2.4874
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1491 - loss: 2.4865 - val_accuracy: 0.1619 - val_loss: 2.2243
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.1875 - loss: 2.1820
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1710 - loss: 2.3347  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1694 - loss: 2.3427
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3406
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1721 - loss: 2.3431
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1720 - loss: 2.3457
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1721 - loss: 2.3476
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1720 - loss: 2.3495
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1719 - loss: 2.3506
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1716 - loss: 2.3515
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3522
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3525
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1705 - loss: 2.3535
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1702 - loss: 2.3542
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3544
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1698 - loss: 2.3543
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1696 - loss: 2.3541
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1695 - loss: 2.3539
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1694 - loss: 2.3535
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3532
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1691 - loss: 2.3530
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1689 - loss: 2.3527
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1687 - loss: 2.3522
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1686 - loss: 2.3517
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1685 - loss: 2.3511
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3506
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1683 - loss: 2.3501
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1682 - loss: 2.3497
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3492
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3488
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3484
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1679 - loss: 2.3480
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1679 - loss: 2.3475
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1679 - loss: 2.3470
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3464
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3459
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3454
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3448
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3443
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3438
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3433
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3429
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3424
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3419
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3414 - val_accuracy: 0.1691 - val_loss: 2.1538
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.0625 - loss: 2.1510
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1736 - loss: 2.2349  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2386
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1795 - loss: 2.2361
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1811 - loss: 2.2384
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1822 - loss: 2.2388
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2388
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2399
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2412
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2416
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2420
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2424
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2429
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2438
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2447
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1853 - loss: 2.2456
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2464
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2469
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1851 - loss: 2.2476
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2483
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2490
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1848 - loss: 2.2496
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2501
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2504
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2506
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2508
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2509
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2508
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2507
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2506
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2505
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2505
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2505
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2505
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2504
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2504
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2503
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2503
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.2502
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.2501
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2500
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2500
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2499
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2498
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2497
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2496 - val_accuracy: 0.1911 - val_loss: 2.0872
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0214
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1877 - loss: 2.1508  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1791 - loss: 2.1680
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1780 - loss: 2.1799
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1805 - loss: 2.1863
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1817 - loss: 2.1924
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1815 - loss: 2.1983
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1815 - loss: 2.2014
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1816 - loss: 2.2031
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1816 - loss: 2.2038
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1813 - loss: 2.2045
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1812 - loss: 2.2052
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1811 - loss: 2.2056
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1812 - loss: 2.2059
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1813 - loss: 2.2062
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1816 - loss: 2.2064
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.2066
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1819 - loss: 2.2070
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1820 - loss: 2.2072
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1821 - loss: 2.2074
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1823 - loss: 2.2076
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2077
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.2078
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.2079
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1831 - loss: 2.2078
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2077
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2076
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1840 - loss: 2.2074
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1843 - loss: 2.2072
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2070
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2068
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2065
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.2063
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1858 - loss: 2.2061
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1861 - loss: 2.2058
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2055
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1866 - loss: 2.2051
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1869 - loss: 2.2047
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1872 - loss: 2.2043
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2039
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1878 - loss: 2.2035
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2031
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1883 - loss: 2.2027
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1885 - loss: 2.2023
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1888 - loss: 2.2020 - val_accuracy: 0.2122 - val_loss: 2.0873
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0675
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2230 - loss: 2.1413  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2101 - loss: 2.1552
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2056 - loss: 2.1621
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2029 - loss: 2.1682
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2026 - loss: 2.1682
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2031 - loss: 2.1663
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2037 - loss: 2.1652
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.1644
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2052 - loss: 2.1638
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2058 - loss: 2.1629
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2064 - loss: 2.1615
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2068 - loss: 2.1602
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2071 - loss: 2.1591
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2073 - loss: 2.1578
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2075 - loss: 2.1566
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2078 - loss: 2.1553
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2082 - loss: 2.1541
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2086 - loss: 2.1530
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2089 - loss: 2.1519
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2093 - loss: 2.1509
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.1499
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2100 - loss: 2.1489
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2102 - loss: 2.1481
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2105 - loss: 2.1472
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2108 - loss: 2.1463
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.1456
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1450
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2115 - loss: 2.1443
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2117 - loss: 2.1437
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2120 - loss: 2.1430
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2123 - loss: 2.1422
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2126 - loss: 2.1416
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2128 - loss: 2.1409
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.1404
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2133 - loss: 2.1398
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2136 - loss: 2.1394
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2138 - loss: 2.1389
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2141 - loss: 2.1385
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2143 - loss: 2.1381
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2145 - loss: 2.1377
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2148 - loss: 2.1373
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2150 - loss: 2.1370
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2153 - loss: 2.1367
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2154 - loss: 2.1365 - val_accuracy: 0.2572 - val_loss: 1.9946
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.0261
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2274 - loss: 2.1388  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2358 - loss: 2.1259
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2357 - loss: 2.1331
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2348 - loss: 2.1343
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2345 - loss: 2.1319
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.1285
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2335 - loss: 2.1251
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2336 - loss: 2.1211
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.1176
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2341 - loss: 2.1147
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2346 - loss: 2.1111
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2350 - loss: 2.1079
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2353 - loss: 2.1054
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2356 - loss: 2.1029
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.1004
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.0981
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2368 - loss: 2.0964
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.0944
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.0928
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.0911
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2386 - loss: 2.0896
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2391 - loss: 2.0881
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2396 - loss: 2.0867
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2400 - loss: 2.0854
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2403 - loss: 2.0843
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2407 - loss: 2.0831
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.0821
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.0811
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2417 - loss: 2.0803
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2420 - loss: 2.0794
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2424 - loss: 2.0786
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2426 - loss: 2.0779
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2428 - loss: 2.0773
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.0767
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.0762
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.0758
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.0753
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2437 - loss: 2.0750
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2438 - loss: 2.0748
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2439 - loss: 2.0745
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2440 - loss: 2.0741
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2441 - loss: 2.0738
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2442 - loss: 2.0735
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2443 - loss: 2.0733 - val_accuracy: 0.2488 - val_loss: 2.0048
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.5861
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2499 - loss: 2.0762  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2569 - loss: 2.0548
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2582 - loss: 2.0521
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2603 - loss: 2.0473
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2617 - loss: 2.0422
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.0394
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2611 - loss: 2.0381
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2612 - loss: 2.0362
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2614 - loss: 2.0344
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.0327
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2617 - loss: 2.0311
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2617 - loss: 2.0298
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.0288
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2617 - loss: 2.0277
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0266
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.0256
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2624 - loss: 2.0247
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2628 - loss: 2.0238
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0231
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0225
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0221
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0217
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2644 - loss: 2.0214
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2646 - loss: 2.0210
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2648 - loss: 2.0208
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0206
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2653 - loss: 2.0205
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2655 - loss: 2.0204
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2657 - loss: 2.0202
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0201
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.0200
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0199
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2663 - loss: 2.0198
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2664 - loss: 2.0197
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2666 - loss: 2.0196
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2667 - loss: 2.0196
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2668 - loss: 2.0195
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2669 - loss: 2.0195
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2670 - loss: 2.0194
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2671 - loss: 2.0193
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2672 - loss: 2.0192
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2673 - loss: 2.0190
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2674 - loss: 2.0189
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2675 - loss: 2.0189 - val_accuracy: 0.3119 - val_loss: 1.9017
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.1523
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2377 - loss: 1.9513  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2505 - loss: 1.9779
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2561 - loss: 1.9793
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2602 - loss: 1.9775
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2621 - loss: 1.9788
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 1.9800
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 1.9809
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2668 - loss: 1.9815
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2681 - loss: 1.9816
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2695 - loss: 1.9813
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2711 - loss: 1.9803
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2723 - loss: 1.9797
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2732 - loss: 1.9794
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2740 - loss: 1.9789
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2746 - loss: 1.9784
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2753 - loss: 1.9779
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 1.9775
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2763 - loss: 1.9771
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 1.9767
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 1.9763
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2776 - loss: 1.9759
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 1.9755
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2784 - loss: 1.9750
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 1.9745
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2791 - loss: 1.9740
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2794 - loss: 1.9736
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 1.9732
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9728
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 1.9725
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2806 - loss: 1.9721
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 1.9717
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 1.9714
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9712
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2816 - loss: 1.9710
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 1.9708
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 1.9706
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9705
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 1.9703
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 1.9701
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2826 - loss: 1.9699
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 1.9699
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 1.9697
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9696
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2831 - loss: 1.9694 - val_accuracy: 0.3256 - val_loss: 1.8486
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.7677
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3561 - loss: 1.8129  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3432 - loss: 1.8429
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3355 - loss: 1.8567
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8668
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8736
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3232 - loss: 1.8804
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3213 - loss: 1.8863
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8918
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8972
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9014
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 1.9050
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.9083
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 1.9110
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 1.9126
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 1.9137
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 1.9146
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3096 - loss: 1.9155
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 1.9165
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 1.9171
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3088 - loss: 1.9175
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3085 - loss: 1.9180
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3083 - loss: 1.9186
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3081 - loss: 1.9191
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3079 - loss: 1.9195
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3078 - loss: 1.9199
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3077 - loss: 1.9203
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 1.9207
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3074 - loss: 1.9210
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3073 - loss: 1.9213
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3072 - loss: 1.9216
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 1.9219
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 1.9222
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3067 - loss: 1.9226
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 1.9229
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9231
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.9234
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 1.9237
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 1.9239
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9241
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 1.9243
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9244
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9245
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9246
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9247
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9247 - val_accuracy: 0.3315 - val_loss: 1.8374
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.7028
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2873 - loss: 1.8929  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2933 - loss: 1.8790
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2971 - loss: 1.8800
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2991 - loss: 1.8835
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3004 - loss: 1.8858
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3022 - loss: 1.8874
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 1.8882
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 1.8885
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 1.8889
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 1.8888
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3079 - loss: 1.8888
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 1.8885
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3088 - loss: 1.8885
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 1.8885
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3093 - loss: 1.8884
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3094 - loss: 1.8881
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 1.8880
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 1.8879
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3094 - loss: 1.8878
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3093 - loss: 1.8880
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 1.8880
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 1.8881
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3091 - loss: 1.8882
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 1.8883
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3090 - loss: 1.8885
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 1.8887
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3088 - loss: 1.8889
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 1.8891
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 1.8893
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 1.8895
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 1.8897
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 1.8898
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 1.8899
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3088 - loss: 1.8900
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3088 - loss: 1.8901
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3088 - loss: 1.8902
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3088 - loss: 1.8902
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 1.8903
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 1.8904
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3090 - loss: 1.8904
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 1.8905
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 1.8905
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 1.8905
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.8905
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3093 - loss: 1.8904 - val_accuracy: 0.3402 - val_loss: 1.8615
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.3153
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2586 - loss: 1.9618  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2778 - loss: 1.9067
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2858 - loss: 1.8848
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2921 - loss: 1.8707
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2976 - loss: 1.8633
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 1.8582
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3067 - loss: 1.8544
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 1.8518
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8501
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 1.8489
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 1.8484
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 1.8477
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 1.8471
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 1.8467
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3159 - loss: 1.8462
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3163 - loss: 1.8459
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3167 - loss: 1.8456
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3172 - loss: 1.8454
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8452
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8450
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3184 - loss: 1.8448
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3187 - loss: 1.8446
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8446
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 1.8448
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8449
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 1.8451
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8452
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 1.8453
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8453
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8453
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 1.8453
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 1.8453
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 1.8453
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3211 - loss: 1.8452
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3212 - loss: 1.8452
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3214 - loss: 1.8452
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3215 - loss: 1.8452
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3217 - loss: 1.8453
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3218 - loss: 1.8454
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 1.8455
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 1.8455
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 1.8456
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 1.8457
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 1.8458
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3225 - loss: 1.8459 - val_accuracy: 0.3562 - val_loss: 1.7958
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5625 - loss: 1.6454
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7709  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3470 - loss: 1.7864
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3424 - loss: 1.7922
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3407 - loss: 1.7929
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3396 - loss: 1.7963
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3386 - loss: 1.7998
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8022
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8038
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8052
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8064
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3376 - loss: 1.8074
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8076
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8079
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8079
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8081
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8083
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8086
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.8086
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8089
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8093
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8096
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.8099
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.8102
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8104
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8107
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3386 - loss: 1.8110
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8112
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8114
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8115
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8116
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8117
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8119
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8121
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8123
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8124
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8124
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8124
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8125
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8125
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8126
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8126
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8126
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8127
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8127 - val_accuracy: 0.3338 - val_loss: 1.8216
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.6883
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7390  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7756
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3504 - loss: 1.7980
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3468 - loss: 1.8091
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 1.8162
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8181
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8185
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8182
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8178
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8166
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8153
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8141
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8132
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8127
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8121
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8111
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8100
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8090
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8079
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8069
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8058
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8046
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8036
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8029
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8024
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8019
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8015
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8010
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8006
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8003
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.7999
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.7996
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.7993
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.7989
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.7985
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.7982
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3406 - loss: 1.7979
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3407 - loss: 1.7975
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3407 - loss: 1.7972
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3408 - loss: 1.7969
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3409 - loss: 1.7965
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 1.7961
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7958
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3412 - loss: 1.7955
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3412 - loss: 1.7955 - val_accuracy: 0.3467 - val_loss: 1.8565
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.5625 - loss: 1.7358
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3946 - loss: 1.7421  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3795 - loss: 1.7321
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3784 - loss: 1.7301
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3745 - loss: 1.7318
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7326
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7360
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7394
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7423
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7454
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7466
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7484
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7506
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7520
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7536
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7546
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7556
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7564
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7571
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7578
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7587
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7594
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7600
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7606
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7610
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7614
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7618
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7621
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7624
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7628
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3617 - loss: 1.7631
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7633
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7635
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7637
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7639
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7641
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7643
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7644
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7646
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7648
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7650
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7652
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7653
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7655
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7656
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7656 - val_accuracy: 0.3608 - val_loss: 1.8178
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.2946
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4340 - loss: 1.6152  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4111 - loss: 1.6590
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3989 - loss: 1.6841
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3908 - loss: 1.7032
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3848 - loss: 1.7157
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3812 - loss: 1.7219
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.7271
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3760 - loss: 1.7304
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7325
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7338
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7348
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7355
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7360
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7366
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7370
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7372
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7375
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7378
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7379
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7382
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7385
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7389
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7392
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7395
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7398
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7401
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7405
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7408
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7411
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7414
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7417
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7420
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7422
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7424
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7426
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7427
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7428
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7428
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7428
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7429
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7430
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7430
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7430
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7430 - val_accuracy: 0.3495 - val_loss: 1.7937
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.8567
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7404  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7411
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7477
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7516
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7549
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7554
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7543
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7526
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7508
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3700 - loss: 1.7496
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7481
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7464
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7446
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7432
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7417
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7403
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7388
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7376
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7366
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7357
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7347
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7339
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7330
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7323
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7316
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7309
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7302
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7297
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7292
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7287
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7283
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7279
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7275
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7270
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7266
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7262
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7258
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7253
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7249
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7245
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7242
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7238
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3720 - loss: 1.7235
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3720 - loss: 1.7232
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3720 - loss: 1.7232 - val_accuracy: 0.3645 - val_loss: 1.8093
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.7378
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3823 - loss: 1.7066  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3758 - loss: 1.7157
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7227
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3736 - loss: 1.7217
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3726 - loss: 1.7186
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7167
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7150
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7129
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3704 - loss: 1.7122
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7112
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7102
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7096
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7098
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7100
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7100
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7099
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7098
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7098
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7099
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7098
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3720 - loss: 1.7098
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7098
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7098
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7097
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7095
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7093
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7091
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7089
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7087
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3730 - loss: 1.7086
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7085
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3732 - loss: 1.7083
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7082
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7081
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7081
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7081
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7081
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7081
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7080
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7080
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7080
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3736 - loss: 1.7080
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3736 - loss: 1.7079
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3736 - loss: 1.7079
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3736 - loss: 1.7079 - val_accuracy: 0.3756 - val_loss: 1.7926
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.4538
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3260 - loss: 1.7993  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3383 - loss: 1.7847
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3446 - loss: 1.7644
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3488 - loss: 1.7548
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3530 - loss: 1.7472
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7426
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7380
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7342
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7305
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7273
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7245
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7218
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7195
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7175
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7158
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7143
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7128
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7116
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7106
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3700 - loss: 1.7093
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7083
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7073
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7062
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3720 - loss: 1.7053
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7044
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7037
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7030
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7022
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3736 - loss: 1.7015
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3738 - loss: 1.7007
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7000
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3743 - loss: 1.6993
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3745 - loss: 1.6988
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3748 - loss: 1.6981
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3749 - loss: 1.6976
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.6971
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.6967
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.6962
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.6957
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3757 - loss: 1.6953
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3758 - loss: 1.6950
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3760 - loss: 1.6945
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3761 - loss: 1.6942
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3762 - loss: 1.6937
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3763 - loss: 1.6937 - val_accuracy: 0.3536 - val_loss: 1.8093
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.3599
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4136 - loss: 1.6413  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4161 - loss: 1.6371
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4120 - loss: 1.6440
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4083 - loss: 1.6505
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4073 - loss: 1.6506
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4065 - loss: 1.6497
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4055 - loss: 1.6496
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4043 - loss: 1.6508
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4029 - loss: 1.6522
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4023 - loss: 1.6524
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4020 - loss: 1.6519
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4016 - loss: 1.6523
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6526
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4005 - loss: 1.6527
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4000 - loss: 1.6527
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3995 - loss: 1.6529
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3991 - loss: 1.6533
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3987 - loss: 1.6538
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3984 - loss: 1.6541
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3980 - loss: 1.6545
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3977 - loss: 1.6549
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3974 - loss: 1.6552
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3972 - loss: 1.6556
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6559
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6562
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6563
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3964 - loss: 1.6564
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6564
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6565
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6565
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3959 - loss: 1.6566
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3958 - loss: 1.6566
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3957 - loss: 1.6566
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3956 - loss: 1.6567
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6568
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6569
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3952 - loss: 1.6571
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6572
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3949 - loss: 1.6573
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3948 - loss: 1.6574
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3947 - loss: 1.6574
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3946 - loss: 1.6575
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3946 - loss: 1.6575
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3945 - loss: 1.6576 - val_accuracy: 0.3441 - val_loss: 1.8607
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.8978
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3882 - loss: 1.6816  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3936 - loss: 1.6696
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3922 - loss: 1.6703
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3938 - loss: 1.6660
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3948 - loss: 1.6629
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3943 - loss: 1.6608
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3945 - loss: 1.6588
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3947 - loss: 1.6571
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3950 - loss: 1.6558
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3950 - loss: 1.6553
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6542
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6532
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3952 - loss: 1.6520
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3952 - loss: 1.6508
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3950 - loss: 1.6495
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3948 - loss: 1.6486
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3946 - loss: 1.6478
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3943 - loss: 1.6473
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3941 - loss: 1.6467
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3940 - loss: 1.6461
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3938 - loss: 1.6458
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3937 - loss: 1.6455
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3936 - loss: 1.6452
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6450
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6448
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3933 - loss: 1.6446
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3933 - loss: 1.6444
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3932 - loss: 1.6441
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3932 - loss: 1.6440
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3931 - loss: 1.6439
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3931 - loss: 1.6438
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6438
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6437
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6437
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6436
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3929 - loss: 1.6436
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3929 - loss: 1.6436
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6436
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6435
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6435
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6435
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6434
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6434 - val_accuracy: 0.3619 - val_loss: 1.8162

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 1s/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:43:48.649045: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:11[0m 1s/step
[1m 49/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m105/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 971us/step
[1m158/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 965us/step
[1m213/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 953us/step
[1m267/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 951us/step
[1m325/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 936us/step
[1m380/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 933us/step
[1m430/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 942us/step
[1m486/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 937us/step
[1m543/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 931us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m57/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 898us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 977us/step
[1m111/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 924us/step
[1m165/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 927us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 37.58 [%]
Global F1 score (validation) = 34.84 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.2196162  0.26104665 0.19260722 ... 0.00452021 0.1424914  0.02605235]
 [0.22756232 0.22421676 0.21935333 ... 0.00123465 0.19664085 0.0322485 ]
 [0.23656313 0.22629833 0.19988869 ... 0.0023146  0.17417939 0.0724693 ]
 ...
 [0.1606509  0.2114008  0.15850325 ... 0.00344661 0.13080639 0.00646527]
 [0.21668145 0.24849586 0.2083331  ... 0.00150965 0.18106273 0.0210958 ]
 [0.18979733 0.19584751 0.1615366  ... 0.01461616 0.113348   0.0537525 ]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.6 [%]
Global accuracy score (test) = 33.72 [%]
Global F1 score (train) = 43.4 [%]
Global F1 score (test) = 31.52 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.20      0.12      0.15       184
 CAMINAR CON MÓVIL O LIBRO       0.22      0.58      0.31       184
       CAMINAR USUAL SPEED       0.00      0.00      0.00       184
            CAMINAR ZIGZAG       0.59      0.47      0.52       184
          DE PIE BARRIENDO       0.33      0.37      0.35       184
   DE PIE DOBLANDO TOALLAS       0.28      0.13      0.18       184
    DE PIE MOVIENDO LIBROS       0.27      0.43      0.33       184
          DE PIE USANDO PC       0.27      0.58      0.37       184
        FASE REPOSO CON K5       0.93      0.62      0.75       184
INCREMENTAL CICLOERGOMETRO       0.69      0.53      0.60       184
           SENTADO LEYENDO       0.22      0.25      0.23       184
         SENTADO USANDO PC       0.00      0.00      0.00       184
      SENTADO VIENDO LA TV       0.34      0.35      0.34       184
   SUBIR Y BAJAR ESCALERAS       0.20      0.12      0.15       184
                    TROTAR       0.37      0.52      0.43       161

                  accuracy                           0.34      2737
                 macro avg       0.33      0.34      0.32      2737
              weighted avg       0.33      0.34      0.31      2737


Accuracy capturado en la ejecución 17: 33.72 [%]
F1-score capturado en la ejecución 17: 31.52 [%]

=== EJECUCIÓN 18 ===

--- TRAIN (ejecución 18) ---

--- TEST (ejecución 18) ---
2025-10-31 15:44:01.781644: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:44:01.792980: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761921841.806287 1700798 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761921841.810546 1700798 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761921841.820593 1700798 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921841.820615 1700798 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921841.820618 1700798 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921841.820619 1700798 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:44:01.823975: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761921844.214419 1700798 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761921847.282411 1700925 service.cc:152] XLA service 0x7c7ad0004070 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761921847.282480 1700925 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:44:07.351007: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761921847.777025 1700925 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761921850.399499 1700925 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45:38[0m 5s/step - accuracy: 0.0625 - loss: 3.3632
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.0680 - loss: 3.3992    
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0742 - loss: 3.3448
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0721 - loss: 3.3323
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0722 - loss: 3.3226
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0739 - loss: 3.3105
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0753 - loss: 3.2958
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0762 - loss: 3.2834
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0772 - loss: 3.2698
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0782 - loss: 3.2567
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0794 - loss: 3.2438
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0810 - loss: 3.2309
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0824 - loss: 3.2181
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0838 - loss: 3.2059
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0849 - loss: 3.1951
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0860 - loss: 3.1846
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0870 - loss: 3.1748
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0881 - loss: 3.1650
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0891 - loss: 3.1551
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0901 - loss: 3.1460
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0909 - loss: 3.1378
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0917 - loss: 3.1293
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0924 - loss: 3.1221
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0932 - loss: 3.1139
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0940 - loss: 3.1057
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0946 - loss: 3.0999
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0953 - loss: 3.0918
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0960 - loss: 3.0848
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0968 - loss: 3.0776
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0976 - loss: 3.0701
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0983 - loss: 3.0634
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0990 - loss: 3.0569
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0996 - loss: 3.0505
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1003 - loss: 3.0437
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1010 - loss: 3.0369
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1017 - loss: 3.0307
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1023 - loss: 3.0245
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1029 - loss: 3.0184
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1035 - loss: 3.0130
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1040 - loss: 3.0081
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1045 - loss: 3.0032
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1050 - loss: 2.9979
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1055 - loss: 2.9934
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1060 - loss: 2.9887
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1060 - loss: 2.9882
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1060 - loss: 2.9880 - val_accuracy: 0.1499 - val_loss: 2.3369
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1250 - loss: 2.1878
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1675 - loss: 2.4538  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1661 - loss: 2.4722
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1612 - loss: 2.4849
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1565 - loss: 2.4940
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4981
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1543 - loss: 2.5004
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1544 - loss: 2.5014
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1546 - loss: 2.5017
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.5010
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1551 - loss: 2.5001
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1551 - loss: 2.4990
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4979
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1549 - loss: 2.4970
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1549 - loss: 2.4959
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1548 - loss: 2.4948
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1549 - loss: 2.4936
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4926
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4915
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4903
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4894
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4884
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4875
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4864
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4855
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1549 - loss: 2.4847
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4838
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1550 - loss: 2.4831
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1551 - loss: 2.4822
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1551 - loss: 2.4814
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1552 - loss: 2.4804
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1552 - loss: 2.4793
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1553 - loss: 2.4783
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1553 - loss: 2.4773
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4763
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4752
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4741
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4731
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1556 - loss: 2.4721
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1556 - loss: 2.4711
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1557 - loss: 2.4700
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1558 - loss: 2.4689
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1559 - loss: 2.4679
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1560 - loss: 2.4670
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1561 - loss: 2.4662 - val_accuracy: 0.1795 - val_loss: 2.1927
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.6042
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1844 - loss: 2.4355  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1833 - loss: 2.4008
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1836 - loss: 2.3806
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1824 - loss: 2.3677
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1805 - loss: 2.3624
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1784 - loss: 2.3582
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1768 - loss: 2.3543
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1755 - loss: 2.3520
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1742 - loss: 2.3509
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.3503
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1730 - loss: 2.3492
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1727 - loss: 2.3484
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1724 - loss: 2.3474
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1721 - loss: 2.3463
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3456
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1716 - loss: 2.3450
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3443
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1713 - loss: 2.3436
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3429
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3422
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3413
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3405
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3397
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3389
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3382
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3375
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3368
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3361
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1713 - loss: 2.3354
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3346
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3338
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1717 - loss: 2.3330
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3322
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1719 - loss: 2.3316
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1721 - loss: 2.3308
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1722 - loss: 2.3302
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1723 - loss: 2.3294
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1725 - loss: 2.3287
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1726 - loss: 2.3280
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1728 - loss: 2.3272
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1730 - loss: 2.3265
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1732 - loss: 2.3258
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1734 - loss: 2.3251
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1735 - loss: 2.3248 - val_accuracy: 0.2520 - val_loss: 2.0976
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.7019
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1762 - loss: 2.2968  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1731 - loss: 2.2953
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1750 - loss: 2.2933
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1780 - loss: 2.2873
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1808 - loss: 2.2823
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1821 - loss: 2.2785
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1833 - loss: 2.2755
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1848 - loss: 2.2715
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2682
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1877 - loss: 2.2649
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1886 - loss: 2.2623
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1893 - loss: 2.2605
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1899 - loss: 2.2591
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1905 - loss: 2.2573
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1911 - loss: 2.2555
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1915 - loss: 2.2541
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1919 - loss: 2.2530
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1922 - loss: 2.2521
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1926 - loss: 2.2510
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1929 - loss: 2.2499
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1933 - loss: 2.2488
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1937 - loss: 2.2479
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1941 - loss: 2.2469
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1944 - loss: 2.2460
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1947 - loss: 2.2451
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1951 - loss: 2.2443
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1954 - loss: 2.2435
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1957 - loss: 2.2427
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1960 - loss: 2.2418
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1962 - loss: 2.2411
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1964 - loss: 2.2403
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1966 - loss: 2.2397
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1968 - loss: 2.2389
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1971 - loss: 2.2382
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1973 - loss: 2.2375
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1975 - loss: 2.2368
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1978 - loss: 2.2360
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1980 - loss: 2.2353
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1981 - loss: 2.2346
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.2341
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1985 - loss: 2.2334
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1987 - loss: 2.2327
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1989 - loss: 2.2320
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1990 - loss: 2.2317 - val_accuracy: 0.2857 - val_loss: 2.0214
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.4711
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1895 - loss: 2.2676  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2087 - loss: 2.2133
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2118 - loss: 2.1885
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2142 - loss: 2.1745
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2175 - loss: 2.1669
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2189 - loss: 2.1635
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2204 - loss: 2.1604
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2214 - loss: 2.1595
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2224 - loss: 2.1587
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2234 - loss: 2.1577
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2239 - loss: 2.1575
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2242 - loss: 2.1575
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2245 - loss: 2.1571
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2247 - loss: 2.1570
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2249 - loss: 2.1573
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1575
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2256 - loss: 2.1576
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2259 - loss: 2.1575
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2261 - loss: 2.1576
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2264 - loss: 2.1576
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2267 - loss: 2.1575
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2270 - loss: 2.1575
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2273 - loss: 2.1574
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2277 - loss: 2.1573
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2280 - loss: 2.1572
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2283 - loss: 2.1570
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2286 - loss: 2.1567
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2289 - loss: 2.1564
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2293 - loss: 2.1560
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2295 - loss: 2.1557
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2297 - loss: 2.1553
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2300 - loss: 2.1548
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2302 - loss: 2.1544
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2304 - loss: 2.1539
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2307 - loss: 2.1534
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2309 - loss: 2.1530
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2311 - loss: 2.1527
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2313 - loss: 2.1523
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2315 - loss: 2.1519
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2316 - loss: 2.1516
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.1512
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.1508
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2322 - loss: 2.1504
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2322 - loss: 2.1504 - val_accuracy: 0.3029 - val_loss: 1.9485
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8964
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0702  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0784
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2680 - loss: 2.0729
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.0699
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2673 - loss: 2.0710
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2666 - loss: 2.0711
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2664 - loss: 2.0707
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2660 - loss: 2.0706
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2656 - loss: 2.0706
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2651 - loss: 2.0711
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2646 - loss: 2.0720
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.0726
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 2.0729
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0729
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2632 - loss: 2.0731
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0733
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0736
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0738
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2628 - loss: 2.0738
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2627 - loss: 2.0739
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2626 - loss: 2.0739
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2626 - loss: 2.0739
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2625 - loss: 2.0738
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2624 - loss: 2.0738
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2623 - loss: 2.0739
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2621 - loss: 2.0740
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2620 - loss: 2.0741
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0741
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0740
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0738
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0735
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0731
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0728
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0723
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0720
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0715
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0712
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0708
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0705
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2620 - loss: 2.0702
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2620 - loss: 2.0699
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2620 - loss: 2.0696
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2621 - loss: 2.0694
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2621 - loss: 2.0694 - val_accuracy: 0.3221 - val_loss: 1.8960
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.2462
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0570  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2580 - loss: 2.0492
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0436
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2652 - loss: 2.0346
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.0262
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2684 - loss: 2.0229
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2692 - loss: 2.0217
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2701 - loss: 2.0210
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0203
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0199
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0197
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.0196
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2727 - loss: 2.0195
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2729 - loss: 2.0192
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2731 - loss: 2.0187
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2733 - loss: 2.0185
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.0185
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2736 - loss: 2.0185
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2737 - loss: 2.0185
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2737 - loss: 2.0185
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2738 - loss: 2.0185
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0184
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2742 - loss: 2.0182
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2744 - loss: 2.0181
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2746 - loss: 2.0178
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2748 - loss: 2.0176
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2750 - loss: 2.0175
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2752 - loss: 2.0173
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2754 - loss: 2.0172
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2755 - loss: 2.0171
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2757 - loss: 2.0170
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2758 - loss: 2.0168
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2759 - loss: 2.0166
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2761 - loss: 2.0165
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2762 - loss: 2.0163
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2763 - loss: 2.0162
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2763 - loss: 2.0159
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2764 - loss: 2.0157
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2765 - loss: 2.0155
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2766 - loss: 2.0154
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 2.0152
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2768 - loss: 2.0151
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2769 - loss: 2.0149 - val_accuracy: 0.3291 - val_loss: 1.8366
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.9120
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2559 - loss: 2.0100  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2621 - loss: 1.9917
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2669 - loss: 1.9818
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2706 - loss: 1.9773
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2738 - loss: 1.9743
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 1.9741
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2775 - loss: 1.9733
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2791 - loss: 1.9717
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 1.9708
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2815 - loss: 1.9697
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2824 - loss: 1.9687
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9680
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 1.9679
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 1.9680
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 1.9680
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 1.9679
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 1.9677
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 1.9676
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2854 - loss: 1.9676
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 1.9677
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 1.9680
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 1.9683
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 1.9685
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2868 - loss: 1.9687
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2870 - loss: 1.9689
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2872 - loss: 1.9689
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2874 - loss: 1.9689
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 1.9690
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2879 - loss: 1.9690
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2881 - loss: 1.9690
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2883 - loss: 1.9690
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2885 - loss: 1.9690
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2887 - loss: 1.9689
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2889 - loss: 1.9688
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2890 - loss: 1.9686
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2892 - loss: 1.9685
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2894 - loss: 1.9684
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2896 - loss: 1.9682
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2898 - loss: 1.9681
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2900 - loss: 1.9679
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2902 - loss: 1.9677
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2904 - loss: 1.9675
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2906 - loss: 1.9673
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2907 - loss: 1.9672 - val_accuracy: 0.3369 - val_loss: 1.8143
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0700
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3136 - loss: 1.9629  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3029 - loss: 1.9610
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9550
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3023 - loss: 1.9490
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 1.9437
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9395
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3063 - loss: 1.9377
[1m 222/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3069 - loss: 1.9368
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3076 - loss: 1.9360
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 1.9352
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 1.9347
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3088 - loss: 1.9341
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3091 - loss: 1.9329
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 1.9324
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3094 - loss: 1.9315
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 1.9304
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 1.9295
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3100 - loss: 1.9285
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 1.9281
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 1.9277
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 1.9275
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3096 - loss: 1.9273
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3095 - loss: 1.9272
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 1.9271
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9270
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9269
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9268
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 1.9266
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9265
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9264
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9262
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9261
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 1.9259
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 1.9258
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 1.9258
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9257
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9257
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9256
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9255
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 1.9253
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 1.9252
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 1.9251
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 1.9250
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3094 - loss: 1.9250 - val_accuracy: 0.3486 - val_loss: 1.8110
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2059
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3470 - loss: 1.8750  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8935
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8899
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3269 - loss: 1.8948
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 1.8965
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8953
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8934
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 1.8927
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3225 - loss: 1.8921
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3213 - loss: 1.8921
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 1.8920
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 1.8919
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 1.8919
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8920
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8923
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8924
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3186 - loss: 1.8924
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8922
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3184 - loss: 1.8919
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8916
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3186 - loss: 1.8912
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3187 - loss: 1.8909
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8907
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8905
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8903
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8902
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8901
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3192 - loss: 1.8899
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8897
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8896
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 1.8893
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8891
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 1.8888
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 1.8885
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 1.8883
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8880
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8878
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8875
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 1.8873
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 1.8872
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 1.8869
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 1.8868
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3209 - loss: 1.8867
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3209 - loss: 1.8866 - val_accuracy: 0.3447 - val_loss: 1.7584
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.2500 - loss: 2.1924
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3150 - loss: 1.8932  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3234 - loss: 1.8946
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3264 - loss: 1.8905
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3273 - loss: 1.8852
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3283 - loss: 1.8816
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 1.8786
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 1.8746
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3294 - loss: 1.8708
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8672
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3309 - loss: 1.8635
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8598
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8567
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3328 - loss: 1.8543
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8529
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 1.8521
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3334 - loss: 1.8512
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8504
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8500
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8499
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8500
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8502
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8503
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8503
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8502
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8501
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8499
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8497
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8495
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8493
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3341 - loss: 1.8491
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8488
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3343 - loss: 1.8487
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8486
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8485
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8484
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8484
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8484
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3343 - loss: 1.8485
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3343 - loss: 1.8485
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3343 - loss: 1.8485
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3343 - loss: 1.8486
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8486
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8486 - val_accuracy: 0.3667 - val_loss: 1.7562
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.1875 - loss: 1.9858
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3197 - loss: 1.9592  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3248 - loss: 1.9327
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 1.9138
[1m 115/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3291 - loss: 1.8991
[1m 144/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3304 - loss: 1.8893
[1m 173/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3310 - loss: 1.8825
[1m 197/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8779
[1m 223/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 1.8728
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 1.8689
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 1.8651
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3348 - loss: 1.8612
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3358 - loss: 1.8578
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.8546
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8520
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8496
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8476
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8458
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8444
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8431
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8419
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8408
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8399
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8391
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8383
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3421 - loss: 1.8376
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3423 - loss: 1.8370
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8363
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8356
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8350
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8344
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8338
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8333
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.8328
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.8323
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.8319
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8316
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8313
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8310
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8307
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8305
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8302
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8300
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8298
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8297 - val_accuracy: 0.3671 - val_loss: 1.7563
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 1.6127
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3622 - loss: 1.6842  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7458
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7654
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3429 - loss: 1.7764
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3417 - loss: 1.7842
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3402 - loss: 1.7898
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3386 - loss: 1.7960
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8002
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.8032
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8052
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3368 - loss: 1.8057
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8061
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8059
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8052
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.8042
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8030
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8020
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8012
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8004
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 1.7997
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3404 - loss: 1.7992
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.7987
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3410 - loss: 1.7983
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3413 - loss: 1.7980
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.7978
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3420 - loss: 1.7973
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3423 - loss: 1.7970
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.7967
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3430 - loss: 1.7964
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3432 - loss: 1.7961
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3435 - loss: 1.7958
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3438 - loss: 1.7954
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3441 - loss: 1.7951
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3445 - loss: 1.7946
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3447 - loss: 1.7943
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3450 - loss: 1.7941
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7939
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7936
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7934
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3459 - loss: 1.7930
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3461 - loss: 1.7927
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3463 - loss: 1.7925
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3465 - loss: 1.7922
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3467 - loss: 1.7920 - val_accuracy: 0.3787 - val_loss: 1.7490
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.9060
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3499 - loss: 1.8209  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3513 - loss: 1.7869
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7629
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7544
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7493
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7460
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7432
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7428
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7425
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7416
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7409
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7399
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7394
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7394
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7394
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7392
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7392
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7394
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7395
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7398
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7402
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7407
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7411
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7414
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7418
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7422
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7427
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7431
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7435
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7439
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7443
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7447
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7451
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7455
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7458
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7460
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7462
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7464
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7466
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7468
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7469
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7471
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7472 - val_accuracy: 0.3724 - val_loss: 1.7602
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.5625 - loss: 1.2820
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3805 - loss: 1.7223  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3773 - loss: 1.7178
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7290
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3740 - loss: 1.7295
[1m 141/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7330
[1m 169/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7346
[1m 196/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7344
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7342
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7333
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7320
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7311
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7305
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7300
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7298
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7298
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7299
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7300
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3704 - loss: 1.7300
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7303
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3700 - loss: 1.7306
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7309
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7312
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7314
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7316
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7318
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7320
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7321
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7322
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7323
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7324
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7325
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7326
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7327
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7327
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7328
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7329
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7330
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7331
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7332
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7333
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7334
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7335
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7335
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7336 - val_accuracy: 0.3845 - val_loss: 1.7582
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.6355
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6828  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3988 - loss: 1.6875
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6799
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3944 - loss: 1.6845
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3903 - loss: 1.6917
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3874 - loss: 1.6967
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3853 - loss: 1.7003
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3837 - loss: 1.7028
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3827 - loss: 1.7035
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3822 - loss: 1.7034
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3816 - loss: 1.7032
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3812 - loss: 1.7028
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3809 - loss: 1.7027
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3808 - loss: 1.7024
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3807 - loss: 1.7024
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3805 - loss: 1.7025
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3803 - loss: 1.7026
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3801 - loss: 1.7026
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3799 - loss: 1.7026
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3798 - loss: 1.7024
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3797 - loss: 1.7023
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3796 - loss: 1.7024
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3794 - loss: 1.7025
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3793 - loss: 1.7027
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7028
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3789 - loss: 1.7029
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3787 - loss: 1.7029
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3786 - loss: 1.7030
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3784 - loss: 1.7031
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7031
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7031
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3781 - loss: 1.7032
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3780 - loss: 1.7033
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3779 - loss: 1.7033
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3779 - loss: 1.7033
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3778 - loss: 1.7034
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3778 - loss: 1.7035
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.7036
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.7037
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3776 - loss: 1.7039
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7040
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7042
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7043
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7043 - val_accuracy: 0.3386 - val_loss: 1.7719
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.4375 - loss: 1.3703
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7029  
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7209
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7244
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7214
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7154
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7101
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7064
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7048
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7036
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.7026
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7018
[1m 329/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3803 - loss: 1.7008
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3809 - loss: 1.7006
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3816 - loss: 1.7003
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6997
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3827 - loss: 1.6991
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6986
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6981
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6978
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6974
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6971
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6968
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3836 - loss: 1.6965
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3836 - loss: 1.6963
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3837 - loss: 1.6961
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3837 - loss: 1.6960
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3838 - loss: 1.6958
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3839 - loss: 1.6956
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3840 - loss: 1.6953
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3841 - loss: 1.6950
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6947
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6946
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6944
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3844 - loss: 1.6942
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3844 - loss: 1.6939
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6937
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6935
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6932
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6930
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3848 - loss: 1.6928
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3848 - loss: 1.6926
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6924
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6922
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3850 - loss: 1.6921 - val_accuracy: 0.3787 - val_loss: 1.7405
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.6916
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4241 - loss: 1.6228  
[1m  58/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4109 - loss: 1.6504
[1m  86/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4048 - loss: 1.6667
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4023 - loss: 1.6717
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4003 - loss: 1.6724
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3986 - loss: 1.6713
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3976 - loss: 1.6704
[1m 224/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3973 - loss: 1.6697
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6690
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6693
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3958 - loss: 1.6696
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6700
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3947 - loss: 1.6701
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3943 - loss: 1.6701
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3940 - loss: 1.6696
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3937 - loss: 1.6692
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6689
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3929 - loss: 1.6686
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3925 - loss: 1.6685
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3922 - loss: 1.6682
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3920 - loss: 1.6680
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6679
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3916 - loss: 1.6678
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3915 - loss: 1.6677
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3914 - loss: 1.6676
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3913 - loss: 1.6675
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3912 - loss: 1.6674
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3911 - loss: 1.6673
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3911 - loss: 1.6671
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3911 - loss: 1.6669
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3911 - loss: 1.6668
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3911 - loss: 1.6666
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3910 - loss: 1.6664
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3910 - loss: 1.6662
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3910 - loss: 1.6660
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3910 - loss: 1.6657
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3910 - loss: 1.6654
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6652
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6650
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6649
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3908 - loss: 1.6649
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3908 - loss: 1.6648
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6648 - val_accuracy: 0.3465 - val_loss: 1.7945
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.6173
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4286 - loss: 1.6531  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4121 - loss: 1.6441
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4068 - loss: 1.6410
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4046 - loss: 1.6403
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4046 - loss: 1.6397
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4054 - loss: 1.6382
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4057 - loss: 1.6374
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4060 - loss: 1.6365
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4063 - loss: 1.6359
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4063 - loss: 1.6353
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4065 - loss: 1.6346
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4066 - loss: 1.6340
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4065 - loss: 1.6340
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4062 - loss: 1.6346
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4058 - loss: 1.6352
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4055 - loss: 1.6356
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4052 - loss: 1.6360
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4050 - loss: 1.6364
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4047 - loss: 1.6366
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4044 - loss: 1.6367
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4041 - loss: 1.6368
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4037 - loss: 1.6370
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4034 - loss: 1.6371
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4031 - loss: 1.6371
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4030 - loss: 1.6370
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4028 - loss: 1.6370
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4026 - loss: 1.6370
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4025 - loss: 1.6371
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4024 - loss: 1.6371
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4022 - loss: 1.6372
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4020 - loss: 1.6375
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4018 - loss: 1.6376
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4016 - loss: 1.6378
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4014 - loss: 1.6379
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4012 - loss: 1.6380
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6381
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4009 - loss: 1.6382
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4008 - loss: 1.6382
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4008 - loss: 1.6382
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4007 - loss: 1.6383
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4006 - loss: 1.6383
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4005 - loss: 1.6384
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4005 - loss: 1.6385
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.4004 - loss: 1.6386 - val_accuracy: 0.3972 - val_loss: 1.7343
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.6250 - loss: 1.2751
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4192 - loss: 1.5203  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4049 - loss: 1.5656
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4016 - loss: 1.5799
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4007 - loss: 1.5866
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4014 - loss: 1.5937
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4032 - loss: 1.5951
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4043 - loss: 1.5945
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4048 - loss: 1.5941
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4055 - loss: 1.5940
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4060 - loss: 1.5935
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4064 - loss: 1.5937
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4066 - loss: 1.5946
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4067 - loss: 1.5958
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4069 - loss: 1.5972
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4069 - loss: 1.5984
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4069 - loss: 1.5991
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4070 - loss: 1.5997
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4070 - loss: 1.6003
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4069 - loss: 1.6009
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4069 - loss: 1.6013
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4069 - loss: 1.6016
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4070 - loss: 1.6018
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4072 - loss: 1.6019
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4073 - loss: 1.6020
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4074 - loss: 1.6021
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.6023
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4076 - loss: 1.6024
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4077 - loss: 1.6026
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4077 - loss: 1.6028
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4078 - loss: 1.6031
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4078 - loss: 1.6033
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4079 - loss: 1.6035
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4079 - loss: 1.6038
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4078 - loss: 1.6040
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4078 - loss: 1.6043
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4078 - loss: 1.6046
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4078 - loss: 1.6049
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4078 - loss: 1.6051
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4077 - loss: 1.6054
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4077 - loss: 1.6055
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4076 - loss: 1.6057
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4076 - loss: 1.6059
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.6060
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.4075 - loss: 1.6061 - val_accuracy: 0.3913 - val_loss: 1.7746
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.6250 - loss: 1.0441
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4247 - loss: 1.5471  
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4275 - loss: 1.5505
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4287 - loss: 1.5499
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4253 - loss: 1.5553
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4225 - loss: 1.5608
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4197 - loss: 1.5674
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4170 - loss: 1.5726
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4150 - loss: 1.5768
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4138 - loss: 1.5790
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4130 - loss: 1.5806
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4122 - loss: 1.5820
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4116 - loss: 1.5831
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4111 - loss: 1.5842
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4105 - loss: 1.5854
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4100 - loss: 1.5868
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4096 - loss: 1.5880
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4094 - loss: 1.5888
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4091 - loss: 1.5894
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4089 - loss: 1.5897
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4087 - loss: 1.5900
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4085 - loss: 1.5902
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4084 - loss: 1.5901
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4083 - loss: 1.5901
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4083 - loss: 1.5903
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4082 - loss: 1.5905
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4081 - loss: 1.5909
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4080 - loss: 1.5912
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4078 - loss: 1.5916
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4077 - loss: 1.5921
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4077 - loss: 1.5925
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4076 - loss: 1.5928
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4076 - loss: 1.5931
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5933
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5935
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5936
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5938
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5939
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5941
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5943
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5945
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5947
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5949
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5951
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.4075 - loss: 1.5951 - val_accuracy: 0.3811 - val_loss: 1.7759

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 1s/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:45:13.432870: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:21[0m 1s/step
[1m 51/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m107/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 958us/step
[1m166/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 921us/step
[1m227/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 896us/step
[1m284/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 893us/step
[1m341/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 892us/step
[1m399/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 888us/step
[1m456/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 888us/step
[1m516/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 882us/step
[1m573/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 882us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 968us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 50/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m103/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 984us/step
[1m154/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 987us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 36.19 [%]
Global F1 score (validation) = 34.01 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.18185508 0.20690925 0.16589443 ... 0.00616544 0.09815772 0.00906744]
 [0.2594521  0.2317305  0.21852091 ... 0.0014896  0.16328384 0.01090901]
 [0.22323579 0.2172021  0.19949713 ... 0.00561448 0.15845391 0.01708108]
 ...
 [0.15047555 0.1896874  0.13647898 ... 0.00771722 0.08470612 0.01072571]
 [0.24295083 0.22475001 0.20372446 ... 0.00255445 0.1601075  0.01140305]
 [0.12611446 0.16028017 0.1295497  ... 0.00461895 0.06415243 0.01467878]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 45.95 [%]
Global accuracy score (test) = 30.65 [%]
Global F1 score (train) = 43.66 [%]
Global F1 score (test) = 28.2 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.18      0.36      0.24       184
 CAMINAR CON MÓVIL O LIBRO       0.19      0.27      0.22       184
       CAMINAR USUAL SPEED       0.00      0.00      0.00       184
            CAMINAR ZIGZAG       0.54      0.41      0.47       184
          DE PIE BARRIENDO       0.22      0.34      0.27       184
   DE PIE DOBLANDO TOALLAS       0.27      0.09      0.14       184
    DE PIE MOVIENDO LIBROS       0.31      0.50      0.38       184
          DE PIE USANDO PC       0.26      0.69      0.38       184
        FASE REPOSO CON K5       0.66      0.39      0.49       184
INCREMENTAL CICLOERGOMETRO       0.73      0.54      0.62       184
           SENTADO LEYENDO       0.06      0.02      0.03       184
         SENTADO USANDO PC       0.34      0.11      0.17       184
      SENTADO VIENDO LA TV       0.26      0.35      0.30       184
   SUBIR Y BAJAR ESCALERAS       0.27      0.05      0.09       184
                    TROTAR       0.39      0.49      0.43       161

                  accuracy                           0.31      2737
                 macro avg       0.31      0.31      0.28      2737
              weighted avg       0.31      0.31      0.28      2737


Accuracy capturado en la ejecución 18: 30.65 [%]
F1-score capturado en la ejecución 18: 28.2 [%]

=== EJECUCIÓN 19 ===

--- TRAIN (ejecución 19) ---

--- TEST (ejecución 19) ---
2025-10-31 15:45:26.715883: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:45:26.727372: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761921926.740777 1704278 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761921926.745057 1704278 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761921926.755089 1704278 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921926.755111 1704278 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921926.755114 1704278 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761921926.755115 1704278 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:45:26.758395: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761921929.125946 1704278 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761921932.247459 1704408 service.cc:152] XLA service 0x7dc4f002caa0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761921932.247502 1704408 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:45:32.312446: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761921932.735817 1704408 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761921935.380046 1704408 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:14[0m 6s/step - accuracy: 0.0000e+00 - loss: 4.3221
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0344 - loss: 3.5348        
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0506 - loss: 3.4124
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0578 - loss: 3.3538
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0624 - loss: 3.3158
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0679 - loss: 3.2804
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0715 - loss: 3.2534
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0735 - loss: 3.2341
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0753 - loss: 3.2173
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0770 - loss: 3.2027
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0786 - loss: 3.1893
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0799 - loss: 3.1777
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0811 - loss: 3.1676
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0824 - loss: 3.1579
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0838 - loss: 3.1474
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0848 - loss: 3.1383
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0859 - loss: 3.1292
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0869 - loss: 3.1197
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0878 - loss: 3.1106
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0887 - loss: 3.1020
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0896 - loss: 3.0937
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0903 - loss: 3.0867
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0911 - loss: 3.0793
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0919 - loss: 3.0713
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0926 - loss: 3.0641
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0934 - loss: 3.0571
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0941 - loss: 3.0502
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0947 - loss: 3.0435
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0954 - loss: 3.0367
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0961 - loss: 3.0303
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0967 - loss: 3.0245
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0973 - loss: 3.0183
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0978 - loss: 3.0133
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0984 - loss: 3.0076
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0990 - loss: 3.0020
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0995 - loss: 2.9967
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1000 - loss: 2.9916
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1006 - loss: 2.9863
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1011 - loss: 2.9814
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1016 - loss: 2.9767
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1020 - loss: 2.9725
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1025 - loss: 2.9678
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1030 - loss: 2.9630
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1035 - loss: 2.9583
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1037 - loss: 2.9567
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1037 - loss: 2.9565 - val_accuracy: 0.1702 - val_loss: 2.2964
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.1875 - loss: 2.4367
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1669 - loss: 2.4368  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1622 - loss: 2.4550
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1617 - loss: 2.4612
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1622 - loss: 2.4653
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1632 - loss: 2.4652
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1636 - loss: 2.4650
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1635 - loss: 2.4646
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1632 - loss: 2.4658
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1629 - loss: 2.4665
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1626 - loss: 2.4672
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1622 - loss: 2.4681
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1619 - loss: 2.4691
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1615 - loss: 2.4698
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1614 - loss: 2.4699
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1613 - loss: 2.4699
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1611 - loss: 2.4696
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1610 - loss: 2.4692
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1608 - loss: 2.4687
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1608 - loss: 2.4678
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1608 - loss: 2.4668
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1609 - loss: 2.4657
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1609 - loss: 2.4648
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1609 - loss: 2.4640
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1609 - loss: 2.4632
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1609 - loss: 2.4624
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1609 - loss: 2.4617
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1609 - loss: 2.4611
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1609 - loss: 2.4605
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1609 - loss: 2.4600
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1608 - loss: 2.4597
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1607 - loss: 2.4594
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1607 - loss: 2.4591
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1606 - loss: 2.4588
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1605 - loss: 2.4584
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1605 - loss: 2.4579
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1604 - loss: 2.4575
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1604 - loss: 2.4570
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1604 - loss: 2.4566
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1604 - loss: 2.4560
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1604 - loss: 2.4555
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1604 - loss: 2.4550
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1604 - loss: 2.4544
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1604 - loss: 2.4538
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1604 - loss: 2.4532
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1604 - loss: 2.4530 - val_accuracy: 0.1904 - val_loss: 2.1829
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4978
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1562 - loss: 2.4233  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1589 - loss: 2.4105
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1590 - loss: 2.4068
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1607 - loss: 2.4013
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1623 - loss: 2.3977
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1642 - loss: 2.3932
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1644 - loss: 2.3913
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1645 - loss: 2.3886
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1646 - loss: 2.3858
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1647 - loss: 2.3835
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3816
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3798
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3784
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1655 - loss: 2.3769
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1657 - loss: 2.3750
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1660 - loss: 2.3733
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1663 - loss: 2.3715
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1666 - loss: 2.3698
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1670 - loss: 2.3680
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1674 - loss: 2.3664
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1677 - loss: 2.3649
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3634
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1682 - loss: 2.3620
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3608
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1686 - loss: 2.3597
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1687 - loss: 2.3588
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1689 - loss: 2.3578
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1690 - loss: 2.3569
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3560
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1693 - loss: 2.3551
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1695 - loss: 2.3542
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1696 - loss: 2.3535
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1698 - loss: 2.3527
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3521
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1700 - loss: 2.3514
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1702 - loss: 2.3507
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1703 - loss: 2.3500
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1704 - loss: 2.3493
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1705 - loss: 2.3486
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1706 - loss: 2.3480
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1707 - loss: 2.3473
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1708 - loss: 2.3467
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3459
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3454 - val_accuracy: 0.2109 - val_loss: 2.0987
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.0057
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1465 - loss: 2.3104  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1530 - loss: 2.3015
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1579 - loss: 2.2948
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1607 - loss: 2.2906
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1628 - loss: 2.2865
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1647 - loss: 2.2833
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1657 - loss: 2.2816
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1664 - loss: 2.2796
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1670 - loss: 2.2779
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1674 - loss: 2.2769
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1678 - loss: 2.2758
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1679 - loss: 2.2749
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1681 - loss: 2.2739
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1683 - loss: 2.2733
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1684 - loss: 2.2727
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1687 - loss: 2.2721
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1690 - loss: 2.2717
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1693 - loss: 2.2716
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1696 - loss: 2.2716
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1699 - loss: 2.2714
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1702 - loss: 2.2710
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1705 - loss: 2.2708
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1707 - loss: 2.2705
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1710 - loss: 2.2701
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1713 - loss: 2.2697
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1716 - loss: 2.2693
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1719 - loss: 2.2689
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1721 - loss: 2.2684
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1724 - loss: 2.2680
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1726 - loss: 2.2676
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1728 - loss: 2.2672
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1730 - loss: 2.2669
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1732 - loss: 2.2666
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1734 - loss: 2.2661
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1736 - loss: 2.2658
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1738 - loss: 2.2654
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1740 - loss: 2.2651
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1741 - loss: 2.2649
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1743 - loss: 2.2646
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1745 - loss: 2.2643
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1746 - loss: 2.2640
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1748 - loss: 2.2637
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1749 - loss: 2.2634
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1749 - loss: 2.2634 - val_accuracy: 0.2453 - val_loss: 2.0450
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.0690
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1526 - loss: 2.3657  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1683 - loss: 2.3165
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1805 - loss: 2.2951
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2839
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1865 - loss: 2.2757
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1882 - loss: 2.2677
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1882 - loss: 2.2602
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1888 - loss: 2.2539
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1891 - loss: 2.2489
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1893 - loss: 2.2450
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1895 - loss: 2.2416
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1896 - loss: 2.2390
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1898 - loss: 2.2367
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1900 - loss: 2.2347
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1900 - loss: 2.2330
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1900 - loss: 2.2316
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1901 - loss: 2.2306
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1903 - loss: 2.2295
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1904 - loss: 2.2286
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1905 - loss: 2.2275
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2266
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2257
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2249
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2242
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2235
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2228
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.2222
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.2216
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.2211
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2205
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2200
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2195
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2191
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1909 - loss: 2.2186
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1909 - loss: 2.2182
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1909 - loss: 2.2179
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1910 - loss: 2.2175
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1910 - loss: 2.2171
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1911 - loss: 2.2168
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1912 - loss: 2.2164
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1913 - loss: 2.2159
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1914 - loss: 2.2156
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1916 - loss: 2.2151
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1916 - loss: 2.2150 - val_accuracy: 0.2496 - val_loss: 2.0089
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1875 - loss: 2.5254
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2118 - loss: 2.2396  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2164 - loss: 2.2081
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2136 - loss: 2.1956
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2114 - loss: 2.1915
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2103 - loss: 2.1861
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2097 - loss: 2.1836
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2094 - loss: 2.1809
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.1785
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2095 - loss: 2.1772
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.1759
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.1748
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2094 - loss: 2.1744
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2092 - loss: 2.1739
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2089 - loss: 2.1736
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1733
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2087 - loss: 2.1728
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2087 - loss: 2.1721
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2087 - loss: 2.1714
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2087 - loss: 2.1709
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2087 - loss: 2.1706
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2087 - loss: 2.1704
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1703
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1702
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1702
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2089 - loss: 2.1702
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2089 - loss: 2.1702
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2090 - loss: 2.1702
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2091 - loss: 2.1702
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2092 - loss: 2.1701
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2093 - loss: 2.1699
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2095 - loss: 2.1697
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2097 - loss: 2.1694
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2098 - loss: 2.1691
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2101 - loss: 2.1687
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2103 - loss: 2.1683
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2105 - loss: 2.1680
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2107 - loss: 2.1676
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1673
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.1669
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1665
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2114 - loss: 2.1661
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2116 - loss: 2.1657
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2117 - loss: 2.1653
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2118 - loss: 2.1651 - val_accuracy: 0.2568 - val_loss: 1.9585
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.6047
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2107 - loss: 2.2489  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2158 - loss: 2.2116
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2168 - loss: 2.2025
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2194 - loss: 2.1910
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2222 - loss: 2.1804
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2234 - loss: 2.1749
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.1688
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.1643
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2272 - loss: 2.1606
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2276 - loss: 2.1575
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.1548
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2282 - loss: 2.1529
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2286 - loss: 2.1506
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2291 - loss: 2.1481
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2294 - loss: 2.1455
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2298 - loss: 2.1431
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2301 - loss: 2.1410
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2304 - loss: 2.1389
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2307 - loss: 2.1372
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2311 - loss: 2.1354
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2314 - loss: 2.1337
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2317 - loss: 2.1322
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2319 - loss: 2.1309
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2322 - loss: 2.1294
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2325 - loss: 2.1281
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2327 - loss: 2.1268
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2329 - loss: 2.1258
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2332 - loss: 2.1248
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2334 - loss: 2.1237
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.1226
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.1217
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.1207
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.1199
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2346 - loss: 2.1190
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2348 - loss: 2.1182
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2350 - loss: 2.1175
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2352 - loss: 2.1168
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2354 - loss: 2.1161
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.1155
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2359 - loss: 2.1149
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2361 - loss: 2.1143
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2363 - loss: 2.1136
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2365 - loss: 2.1130
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2366 - loss: 2.1128 - val_accuracy: 0.3267 - val_loss: 1.8738
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 1.9205
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9954  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2893 - loss: 2.0072
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2901 - loss: 2.0142
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2854 - loss: 2.0237
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2820 - loss: 2.0311
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2789 - loss: 2.0386
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2766 - loss: 2.0424
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2749 - loss: 2.0441
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2736 - loss: 2.0447
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.0452
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0456
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2707 - loss: 2.0462
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2697 - loss: 2.0470
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2690 - loss: 2.0475
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2684 - loss: 2.0475
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.0474
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.0473
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.0475
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2668 - loss: 2.0478
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2665 - loss: 2.0480
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2662 - loss: 2.0481
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2660 - loss: 2.0482
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0483
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2656 - loss: 2.0484
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2654 - loss: 2.0485
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2653 - loss: 2.0485
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2652 - loss: 2.0484
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2651 - loss: 2.0484
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0483
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2649 - loss: 2.0482
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2648 - loss: 2.0480
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2648 - loss: 2.0478
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2648 - loss: 2.0475
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2648 - loss: 2.0472
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2648 - loss: 2.0470
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2649 - loss: 2.0468
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2649 - loss: 2.0466
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2649 - loss: 2.0463
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0460
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0458
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0455
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0453
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0450
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2651 - loss: 2.0449 - val_accuracy: 0.3147 - val_loss: 1.8423
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.0935
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2865 - loss: 1.9834  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2850 - loss: 1.9732
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2858 - loss: 1.9657
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2847 - loss: 1.9679
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9740
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 1.9788
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 1.9813
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9826
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 1.9836
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 1.9850
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 1.9860
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 1.9865
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 1.9866
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 1.9866
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 1.9870
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 1.9876
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 1.9881
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 1.9887
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 1.9893
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 1.9898
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 1.9902
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 1.9904
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 1.9905
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 1.9907
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 1.9908
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 1.9910
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9912
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9912
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2801 - loss: 1.9912
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 1.9912
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2804 - loss: 1.9911
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 1.9911
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2806 - loss: 1.9912
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 1.9912
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2808 - loss: 1.9912
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 1.9912
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2811 - loss: 1.9911
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2813 - loss: 1.9910
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2815 - loss: 1.9909
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 1.9908
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 1.9907
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2820 - loss: 1.9906
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9905
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2822 - loss: 1.9905 - val_accuracy: 0.3375 - val_loss: 1.8049
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2785
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2493 - loss: 2.0093  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2533 - loss: 1.9930
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2578 - loss: 1.9866
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2630 - loss: 1.9797
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2664 - loss: 1.9757
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2695 - loss: 1.9713
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2719 - loss: 1.9678
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2735 - loss: 1.9659
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2749 - loss: 1.9652
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 1.9643
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 1.9633
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 1.9623
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9611
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2811 - loss: 1.9600
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 1.9592
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 1.9584
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 1.9575
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 1.9567
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 1.9559
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2853 - loss: 1.9552
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 1.9546
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 1.9540
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2868 - loss: 1.9536
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2873 - loss: 1.9532
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 1.9528
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2881 - loss: 1.9524
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2884 - loss: 1.9520
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2889 - loss: 1.9517
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 1.9513
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2897 - loss: 1.9509
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2900 - loss: 1.9506
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2904 - loss: 1.9504
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2907 - loss: 1.9502
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 1.9500
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2913 - loss: 1.9498
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2916 - loss: 1.9497
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 1.9496
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 1.9495
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 1.9494
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9493
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 1.9491
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2931 - loss: 1.9489
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2933 - loss: 1.9487
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2934 - loss: 1.9485 - val_accuracy: 0.3469 - val_loss: 1.7717
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.0174
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2899 - loss: 1.9127  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9127
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2937 - loss: 1.9130
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2939 - loss: 1.9160
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9173
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 1.9198
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9235
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9259
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2950 - loss: 1.9267
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9285
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9297
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9304
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9306
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9304
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9304
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 1.9302
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 1.9300
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2979 - loss: 1.9299
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9299
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9300
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2988 - loss: 1.9302
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 1.9304
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9306
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 1.9307
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 1.9308
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 1.9308
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9308
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9306
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3012 - loss: 1.9304
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 1.9302
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9299
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 1.9296
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 1.9293
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 1.9289
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 1.9284
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3031 - loss: 1.9280
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3033 - loss: 1.9276
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 1.9272
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9268
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9265
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3042 - loss: 1.9261
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3044 - loss: 1.9258
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 1.9255
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 1.9252
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3048 - loss: 1.9250 - val_accuracy: 0.3639 - val_loss: 1.7670
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9681
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3306 - loss: 1.9234  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3261 - loss: 1.9131
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3287 - loss: 1.8952
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3278 - loss: 1.8905
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3280 - loss: 1.8871
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 1.8822
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8787
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3308 - loss: 1.8769
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8755
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 1.8739
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3321 - loss: 1.8728
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3322 - loss: 1.8723
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8720
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3322 - loss: 1.8720
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3321 - loss: 1.8720
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 1.8718
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 1.8719
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 1.8718
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8719
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3314 - loss: 1.8720
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8720
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8721
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8720
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8719
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3310 - loss: 1.8717
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 1.8716
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3309 - loss: 1.8715
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3308 - loss: 1.8716
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 1.8717
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 1.8717
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8718
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 1.8717
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 1.8716
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 1.8715
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8713
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8712
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8710
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 1.8709
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 1.8708
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8707
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8706
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8704
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3298 - loss: 1.8703
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3298 - loss: 1.8701
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3298 - loss: 1.8701 - val_accuracy: 0.3636 - val_loss: 1.7532
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.4375 - loss: 1.7859
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3582 - loss: 1.8432  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3523 - loss: 1.8475
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3468 - loss: 1.8459
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8466
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8457
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8439
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8425
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8417
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8416
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8411
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8405
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8398
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8396
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8390
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8384
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8378
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8374
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8372
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8369
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8367
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8367
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.8369
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8370
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8372
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3378 - loss: 1.8375
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.8377
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.8379
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3373 - loss: 1.8380
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8380
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8381
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8382
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8383
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8384
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8384
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8384
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8384
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3369 - loss: 1.8384
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3369 - loss: 1.8385
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8385
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8385
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8385
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8386
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8386
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8387
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8387 - val_accuracy: 0.3449 - val_loss: 1.7709
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 2.3773
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8522  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3310 - loss: 1.8426
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8336
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3324 - loss: 1.8246
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8203
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3326 - loss: 1.8204
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 1.8226
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8245
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8263
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8275
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 1.8281
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3321 - loss: 1.8284
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.8285
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 1.8286
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8289
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 1.8292
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8295
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8297
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8297
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8296
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8294
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8290
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8284
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3346 - loss: 1.8279
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3348 - loss: 1.8273
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3350 - loss: 1.8268
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3351 - loss: 1.8265
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8262
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8259
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3355 - loss: 1.8256
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3356 - loss: 1.8252
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3358 - loss: 1.8249
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8245
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8241
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8237
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8234
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8231
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8229
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8226
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8223
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3367 - loss: 1.8220
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3368 - loss: 1.8218
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3369 - loss: 1.8216
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3369 - loss: 1.8214 - val_accuracy: 0.3549 - val_loss: 1.7620
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.4708
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7709  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3548 - loss: 1.8023
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3593 - loss: 1.8021
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3612 - loss: 1.8000
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7990
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7987
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7974
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7954
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7937
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7922
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7913
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7909
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7909
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7904
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7900
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7896
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7890
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7887
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7884
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7882
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7878
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7875
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7872
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7869
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7866
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7863
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7859
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7855
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7851
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7848
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7846
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7845
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7843
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7841
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7839
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7837
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7836
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7834
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7832
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7830
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7830
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7830
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7829
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7830
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7830 - val_accuracy: 0.3580 - val_loss: 1.7862
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.4654
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3736 - loss: 1.8328  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7809
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7685
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7609
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7580
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7566
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7556
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7543
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7536
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7533
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7529
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7526
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7523
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7521
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7521
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7522
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7523
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7524
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7526
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7528
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7529
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7530
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7531
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7532
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7533
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7534
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7533
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7534
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7534
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7535
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7535
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7535
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7535
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7535
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7535
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7535
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7535
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7536
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7536
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7536
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7535
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7535
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7534
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7534 - val_accuracy: 0.3504 - val_loss: 1.7693
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.4375 - loss: 1.6731
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3801 - loss: 1.6315  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3776 - loss: 1.6611
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3749 - loss: 1.6799
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3738 - loss: 1.6876
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3728 - loss: 1.6923
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3720 - loss: 1.6969
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3716 - loss: 1.6989
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7003
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7026
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7042
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7052
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7063
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7073
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7086
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7095
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7102
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7107
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7110
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7114
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7116
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7118
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7119
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7120
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7121
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7123
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7126
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7129
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7131
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7134
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7137
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7140
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7143
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7145
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7148
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7151
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7153
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7156
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7158
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7160
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7162
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7164
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7167
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7169 - val_accuracy: 0.3660 - val_loss: 1.7601

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 1s/step
[1m49/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:46:28.253046: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:30[0m 1s/step
[1m 53/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 976us/step
[1m110/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 928us/step
[1m168/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 906us/step
[1m227/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 893us/step
[1m281/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 901us/step
[1m336/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 903us/step
[1m386/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 918us/step
[1m437/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 927us/step
[1m490/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 930us/step
[1m547/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 925us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 47/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m 96/169[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m151/169[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 38.11 [%]
Global F1 score (validation) = 35.17 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.08634089 0.07186431 0.06861819 ... 0.05379266 0.10323881 0.21440856]
 [0.16109203 0.20455427 0.1329386  ... 0.00620583 0.06935553 0.00743824]
 [0.12939823 0.11803529 0.12403211 ... 0.01060399 0.18419826 0.2753149 ]
 ...
 [0.22771011 0.21230075 0.21576516 ... 0.0054184  0.17042224 0.02302402]
 [0.22472215 0.19478367 0.22848049 ... 0.00172036 0.15708117 0.00854851]
 [0.18172541 0.23398021 0.1453515  ... 0.00364622 0.06658288 0.00590631]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 47.95 [%]
Global accuracy score (test) = 33.14 [%]
Global F1 score (train) = 44.81 [%]
Global F1 score (test) = 30.92 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.23      0.37      0.29       184
 CAMINAR CON MÓVIL O LIBRO       0.30      0.28      0.29       184
       CAMINAR USUAL SPEED       0.21      0.11      0.14       184
            CAMINAR ZIGZAG       0.54      0.44      0.49       184
          DE PIE BARRIENDO       0.24      0.35      0.29       184
   DE PIE DOBLANDO TOALLAS       0.43      0.02      0.03       184
    DE PIE MOVIENDO LIBROS       0.29      0.55      0.38       184
          DE PIE USANDO PC       0.33      0.60      0.43       184
        FASE REPOSO CON K5       0.70      0.40      0.51       184
INCREMENTAL CICLOERGOMETRO       0.70      0.57      0.62       184
           SENTADO LEYENDO       0.25      0.46      0.32       184
         SENTADO USANDO PC       0.30      0.26      0.28       184
      SENTADO VIENDO LA TV       0.00      0.00      0.00       184
   SUBIR Y BAJAR ESCALERAS       0.26      0.18      0.21       184
                    TROTAR       0.33      0.39      0.36       161

                  accuracy                           0.33      2737
                 macro avg       0.34      0.33      0.31      2737
              weighted avg       0.34      0.33      0.31      2737


Accuracy capturado en la ejecución 19: 33.14 [%]
F1-score capturado en la ejecución 19: 30.92 [%]

=== EJECUCIÓN 20 ===

--- TRAIN (ejecución 20) ---

--- TEST (ejecución 20) ---
2025-10-31 15:46:41.456383: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:46:41.467675: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761922001.480719 1707280 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761922001.485038 1707280 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761922001.494881 1707280 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922001.494900 1707280 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922001.494902 1707280 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922001.494904 1707280 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:46:41.498165: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761922003.886214 1707280 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761922007.005751 1707388 service.cc:152] XLA service 0x77ccd401bd40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761922007.005815 1707388 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:46:47.070649: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761922007.493037 1707388 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761922010.160881 1707388 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:19[0m 6s/step - accuracy: 0.0000e+00 - loss: 3.6832
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.0349 - loss: 3.3309        
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0466 - loss: 3.3248
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0527 - loss: 3.3128
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0579 - loss: 3.2948
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0621 - loss: 3.2767
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0651 - loss: 3.2608
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0670 - loss: 3.2481
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0690 - loss: 3.2355
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0704 - loss: 3.2248
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0718 - loss: 3.2146
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0732 - loss: 3.2041
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0743 - loss: 3.1954
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0755 - loss: 3.1858
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0764 - loss: 3.1770
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0773 - loss: 3.1692
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0782 - loss: 3.1611
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0792 - loss: 3.1530
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0802 - loss: 3.1446
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0811 - loss: 3.1376
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0821 - loss: 3.1298
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0830 - loss: 3.1231
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0839 - loss: 3.1161
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0848 - loss: 3.1090
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0857 - loss: 3.1020
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0866 - loss: 3.0952
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0875 - loss: 3.0888
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0883 - loss: 3.0820
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0891 - loss: 3.0756
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0898 - loss: 3.0694
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0905 - loss: 3.0633
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0912 - loss: 3.0574
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0919 - loss: 3.0514
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0926 - loss: 3.0452
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0932 - loss: 3.0394
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0938 - loss: 3.0340
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0944 - loss: 3.0282
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0950 - loss: 3.0225
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0956 - loss: 3.0167
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0961 - loss: 3.0118
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0966 - loss: 3.0069
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0971 - loss: 3.0018
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0975 - loss: 2.9973
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.0979 - loss: 2.9936
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.0979 - loss: 2.9934 - val_accuracy: 0.1845 - val_loss: 2.3271
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.1875 - loss: 2.3491
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1756 - loss: 2.4554  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1520 - loss: 2.4831
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1463 - loss: 2.4898
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1440 - loss: 2.4955
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1434 - loss: 2.4956
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1429 - loss: 2.4953
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1425 - loss: 2.4952
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1426 - loss: 2.4941
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1427 - loss: 2.4937
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1428 - loss: 2.4942
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1430 - loss: 2.4947
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1435 - loss: 2.4948
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1439 - loss: 2.4950
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1443 - loss: 2.4949
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1447 - loss: 2.4949
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1449 - loss: 2.4947
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1452 - loss: 2.4945
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1455 - loss: 2.4942
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1458 - loss: 2.4938
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1461 - loss: 2.4933
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1462 - loss: 2.4929
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1465 - loss: 2.4923
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1467 - loss: 2.4917
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1469 - loss: 2.4909
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1471 - loss: 2.4901
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1473 - loss: 2.4894
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1475 - loss: 2.4886
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1476 - loss: 2.4879
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1478 - loss: 2.4871
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1480 - loss: 2.4863
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1482 - loss: 2.4855
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1484 - loss: 2.4848
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1486 - loss: 2.4840
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1488 - loss: 2.4832
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1490 - loss: 2.4824
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1491 - loss: 2.4816
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1493 - loss: 2.4808
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1495 - loss: 2.4800
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1497 - loss: 2.4792
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1498 - loss: 2.4784
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1500 - loss: 2.4776
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1501 - loss: 2.4767
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1503 - loss: 2.4759
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1504 - loss: 2.4755 - val_accuracy: 0.1941 - val_loss: 2.1968
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.0625 - loss: 2.4839
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1277 - loss: 2.4476  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1415 - loss: 2.4102
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1452 - loss: 2.4010
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1468 - loss: 2.3978
[1m 140/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1493 - loss: 2.3913
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1506 - loss: 2.3876
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1517 - loss: 2.3840
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1525 - loss: 2.3808
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1532 - loss: 2.3778
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1540 - loss: 2.3750
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1546 - loss: 2.3724
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.3702
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1555 - loss: 2.3681
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1560 - loss: 2.3662
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1564 - loss: 2.3648
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1568 - loss: 2.3631
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1573 - loss: 2.3616
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1577 - loss: 2.3603
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1581 - loss: 2.3592
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1586 - loss: 2.3581
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1589 - loss: 2.3571
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1593 - loss: 2.3562
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1598 - loss: 2.3551
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1602 - loss: 2.3541
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1605 - loss: 2.3531
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1608 - loss: 2.3523
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1610 - loss: 2.3515
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1613 - loss: 2.3508
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1616 - loss: 2.3501
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1618 - loss: 2.3496
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1620 - loss: 2.3491
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1622 - loss: 2.3485
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1624 - loss: 2.3479
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1626 - loss: 2.3473
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1628 - loss: 2.3467
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1630 - loss: 2.3462
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1631 - loss: 2.3458
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1633 - loss: 2.3453
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1634 - loss: 2.3448
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1636 - loss: 2.3444
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1638 - loss: 2.3439
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1640 - loss: 2.3434
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1642 - loss: 2.3429
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1643 - loss: 2.3424
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1644 - loss: 2.3422 - val_accuracy: 0.2289 - val_loss: 2.1433
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.0408
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1953 - loss: 2.2013  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1964 - loss: 2.2167
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1975 - loss: 2.2368
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1970 - loss: 2.2510
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1954 - loss: 2.2583
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1936 - loss: 2.2651
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1919 - loss: 2.2707
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2745
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1900 - loss: 2.2765
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1896 - loss: 2.2780
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1894 - loss: 2.2788
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1894 - loss: 2.2788
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1895 - loss: 2.2785
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1894 - loss: 2.2781
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1893 - loss: 2.2776
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1893 - loss: 2.2771
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1894 - loss: 2.2765
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1895 - loss: 2.2759
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1896 - loss: 2.2754
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1898 - loss: 2.2746
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1899 - loss: 2.2737
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1901 - loss: 2.2731
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1901 - loss: 2.2727
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1901 - loss: 2.2722
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1902 - loss: 2.2717
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1903 - loss: 2.2712
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1903 - loss: 2.2707
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1903 - loss: 2.2704
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1904 - loss: 2.2700
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1904 - loss: 2.2697
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1905 - loss: 2.2692
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1905 - loss: 2.2688
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1905 - loss: 2.2685
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2682
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2679
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2677
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1906 - loss: 2.2675
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.2673
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.2672
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.2670
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.2668
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.2666
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2663
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2662
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2661 - val_accuracy: 0.2339 - val_loss: 2.0946
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.4878
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2104 - loss: 2.2951  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2116 - loss: 2.2559
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2133 - loss: 2.2358
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2137 - loss: 2.2292
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2144 - loss: 2.2244
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2148 - loss: 2.2213
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2154 - loss: 2.2186
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2157 - loss: 2.2165
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2156 - loss: 2.2153
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2153 - loss: 2.2146
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2151 - loss: 2.2142
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2149 - loss: 2.2140
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2149 - loss: 2.2133
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2150 - loss: 2.2125
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2149 - loss: 2.2115
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2148 - loss: 2.2109
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.2103
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2145 - loss: 2.2099
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2143 - loss: 2.2095
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2141 - loss: 2.2093
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2139 - loss: 2.2089
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2137 - loss: 2.2087
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2136 - loss: 2.2084
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2135 - loss: 2.2081
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2134 - loss: 2.2078
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2133 - loss: 2.2075
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2133 - loss: 2.2072
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.2068
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.2065
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.2061
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.2059
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.2056
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.2054
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.2052
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.2050
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.2048
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.2046
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.2044
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.2042
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.2040
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.2037
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.2035
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.2033
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.2030
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2132 - loss: 2.2029 - val_accuracy: 0.2278 - val_loss: 2.0509
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2198
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2294 - loss: 2.1545  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2323 - loss: 2.1390
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2358 - loss: 2.1344
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1327
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2375 - loss: 2.1325
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1348
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2366 - loss: 2.1358
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2363 - loss: 2.1365
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2363 - loss: 2.1375
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.1384
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.1386
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2365 - loss: 2.1385
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2367 - loss: 2.1383
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2369 - loss: 2.1380
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1379
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1380
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1383
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1385
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1387
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2374 - loss: 2.1388
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2374 - loss: 2.1389
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1390
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1390
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1390
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1390
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1390
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1390
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1389
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1389
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1388
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2370 - loss: 2.1387
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2370 - loss: 2.1386
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2370 - loss: 2.1384
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1382
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1379
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1378
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1375
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1373
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.1371
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1369
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1367
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1365
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1362
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2373 - loss: 2.1360
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2374 - loss: 2.1359 - val_accuracy: 0.2945 - val_loss: 1.9396
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.1250 - loss: 2.1233
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2128 - loss: 2.0594  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2262 - loss: 2.0566
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2299 - loss: 2.0652
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2324 - loss: 2.0702
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2354 - loss: 2.0701
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2374 - loss: 2.0702
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2390 - loss: 2.0687
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2405 - loss: 2.0670
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2417 - loss: 2.0661
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.0653
[1m 302/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2436 - loss: 2.0652
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2445 - loss: 2.0653
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2453 - loss: 2.0653
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.0656
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2467 - loss: 2.0655
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2474 - loss: 2.0653
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.0652
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2484 - loss: 2.0650
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2488 - loss: 2.0647
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2493 - loss: 2.0644
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.0644
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2501 - loss: 2.0644
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0645
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2506 - loss: 2.0644
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.0643
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.0643
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2514 - loss: 2.0642
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0643
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2518 - loss: 2.0642
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2520 - loss: 2.0642
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2523 - loss: 2.0640
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2525 - loss: 2.0639
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2526 - loss: 2.0637
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2528 - loss: 2.0635
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2530 - loss: 2.0633
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.0632
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2534 - loss: 2.0631
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2536 - loss: 2.0629
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0628
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2540 - loss: 2.0627
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2541 - loss: 2.0626
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.0625
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.0624
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2545 - loss: 2.0624 - val_accuracy: 0.3134 - val_loss: 1.8692
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1722
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2388 - loss: 2.0759  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2350 - loss: 2.0889
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2385 - loss: 2.0851
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2432 - loss: 2.0786
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2476 - loss: 2.0709
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2518 - loss: 2.0625
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2542 - loss: 2.0567
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2561 - loss: 2.0528
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2581 - loss: 2.0492
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.0459
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2611 - loss: 2.0435
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.0417
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0396
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0377
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0363
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2659 - loss: 2.0348
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2665 - loss: 2.0337
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.0326
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.0316
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2681 - loss: 2.0307
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2685 - loss: 2.0297
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2689 - loss: 2.0289
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.0280
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.0271
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.0263
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.0254
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0246
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.0238
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0231
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0225
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0219
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0213
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0207
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0202
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0197
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2723 - loss: 2.0193
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2724 - loss: 2.0190
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.0186
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0183
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.0180
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.0177
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2728 - loss: 2.0175
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 2.0173
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2730 - loss: 2.0171 - val_accuracy: 0.3140 - val_loss: 1.8342
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.9601
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9224  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3083 - loss: 1.9384
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3066 - loss: 1.9404
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3066 - loss: 1.9413
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3046 - loss: 1.9433
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3024 - loss: 1.9455
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9472
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9487
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 1.9502
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2964 - loss: 1.9509
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 1.9516
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2957 - loss: 1.9527
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9544
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9562
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 1.9572
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 1.9578
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9583
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9588
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 1.9593
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 1.9596
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 1.9598
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 1.9600
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 1.9603
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2931 - loss: 1.9606
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2930 - loss: 1.9609
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 1.9612
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 1.9615
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 1.9617
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9619
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9620
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9621
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9621
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 1.9622
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 1.9622
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 1.9622
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 1.9623
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 1.9624
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9624
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9624
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 1.9625
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 1.9626
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 1.9627
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 1.9628
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 1.9628
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2920 - loss: 1.9629 - val_accuracy: 0.3323 - val_loss: 1.8018
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.6045
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3012 - loss: 1.8847  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9012
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3033 - loss: 1.9069
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3027 - loss: 1.9128
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3027 - loss: 1.9155
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9151
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9161
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 1.9176
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 1.9188
[1m 274/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9188
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9190
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9192
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9193
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9194
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9194
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 1.9193
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 1.9190
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 1.9188
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 1.9185
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 1.9183
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 1.9182
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 1.9182
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9181
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9181
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9182
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9182
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9182
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9182
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9182
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9182
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9182
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9181
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9182
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9183
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9185
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9187
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9188
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9190
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9191
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9192
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3050 - loss: 1.9193
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3050 - loss: 1.9195
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3050 - loss: 1.9196
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3050 - loss: 1.9196 - val_accuracy: 0.3426 - val_loss: 1.7851
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.8709
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3222 - loss: 1.8399  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3160 - loss: 1.8482
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3143 - loss: 1.8583
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3138 - loss: 1.8644
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3137 - loss: 1.8666
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3129 - loss: 1.8680
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 1.8693
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 1.8702
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8708
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 1.8711
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8715
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8718
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 1.8726
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 1.8734
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 1.8744
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 1.8753
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8763
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 1.8771
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8776
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8781
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8786
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 1.8790
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 1.8793
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 1.8796
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 1.8799
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 1.8801
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 1.8803
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 1.8804
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 1.8805
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 1.8805
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 1.8805
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 1.8805
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 1.8804
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 1.8804
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 1.8805
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 1.8806
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 1.8807
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 1.8808
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 1.8809
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 1.8810
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 1.8810
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 1.8811
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 1.8811
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3129 - loss: 1.8812 - val_accuracy: 0.3547 - val_loss: 1.7671
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.5995
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9407  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3000 - loss: 1.9108
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3030 - loss: 1.8981
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3057 - loss: 1.8909
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3075 - loss: 1.8839
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 1.8810
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 1.8794
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 1.8778
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 1.8760
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 1.8742
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 1.8730
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 1.8716
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8702
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8687
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8670
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8655
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8644
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3209 - loss: 1.8633
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 1.8627
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 1.8622
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 1.8617
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3227 - loss: 1.8614
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 1.8610
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 1.8608
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 1.8604
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 1.8600
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 1.8597
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8594
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8592
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3243 - loss: 1.8590
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8588
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8586
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 1.8585
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 1.8584
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 1.8582
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3253 - loss: 1.8581
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 1.8579
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 1.8577
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 1.8574
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8571
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 1.8569
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 1.8566
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3264 - loss: 1.8564
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3264 - loss: 1.8563 - val_accuracy: 0.3528 - val_loss: 1.7820
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9359
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8097  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8017
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3303 - loss: 1.8006
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3304 - loss: 1.8031
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8074
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8114
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8145
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8167
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 1.8180
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8191
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8203
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8216
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8229
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8240
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8251
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3308 - loss: 1.8262
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 1.8270
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8276
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8281
[1m 542/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8286
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3300 - loss: 1.8290
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8294
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8297
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3298 - loss: 1.8299
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3298 - loss: 1.8300
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8300
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8301
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8302
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 1.8303
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 1.8304
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 1.8304
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8304
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8303
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8303
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8303
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8303
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8302
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 1.8302
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 1.8301
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 1.8301
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 1.8301
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8301
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8301
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8301 - val_accuracy: 0.3393 - val_loss: 1.7729
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.9636
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8581  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8290
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8135
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8016
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3370 - loss: 1.7944
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3373 - loss: 1.7900
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.7882
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3358 - loss: 1.7876
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3352 - loss: 1.7878
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3347 - loss: 1.7891
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3341 - loss: 1.7914
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 1.7932
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3334 - loss: 1.7949
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3332 - loss: 1.7963
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 1.7978
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3326 - loss: 1.7991
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3324 - loss: 1.8004
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8013
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8020
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8026
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.8030
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 1.8034
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 1.8038
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8042
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3332 - loss: 1.8045
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8047
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3337 - loss: 1.8048
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8049
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3341 - loss: 1.8048
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3343 - loss: 1.8048
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8048
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3346 - loss: 1.8047
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8045
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3349 - loss: 1.8043
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3351 - loss: 1.8041
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3352 - loss: 1.8039
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8037
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3356 - loss: 1.8034
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3358 - loss: 1.8032
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8030
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8028
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8025
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.8023
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3366 - loss: 1.8020
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3367 - loss: 1.8019 - val_accuracy: 0.3652 - val_loss: 1.7565
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7401
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3773 - loss: 1.6433  
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3701 - loss: 1.6709
[1m  85/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3671 - loss: 1.6937
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7073
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7175
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7230
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7275
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7302
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7326
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7351
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7383
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7410
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7438
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7460
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7476
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7489
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7502
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7513
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7525
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7536
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7544
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7554
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7563
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7571
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7579
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7586
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7593
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3559 - loss: 1.7601
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3557 - loss: 1.7606
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3555 - loss: 1.7611
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7616
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7622
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7626
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7630
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7634
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7638
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3541 - loss: 1.7641
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3540 - loss: 1.7643
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7646
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7649
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7652
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7654
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7657
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7660
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3532 - loss: 1.7661 - val_accuracy: 0.3719 - val_loss: 1.7478
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.5625 - loss: 1.5689
[1m  30/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7534  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7623
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7617
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7627
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7638
[1m 168/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7639
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7633
[1m 222/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7624
[1m 249/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7618
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7611
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7607
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7603
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7602
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7599
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7601
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7601
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7599
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7598
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7594
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7591
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7589
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7588
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7588
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7587
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7586
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7585
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7583
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7583
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7582
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7579
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7577
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7575
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7572
[1m 913/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7571
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7569
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7567
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7565
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7563
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7561
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7560
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7558
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7557
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7556
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7555 - val_accuracy: 0.3796 - val_loss: 1.7456
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.9693
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3417 - loss: 1.7341  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7427
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7401
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7385
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7368
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7357
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7355
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7353
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7351
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7349
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7351
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7350
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7348
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7345
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7342
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7343
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7347
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7349
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7349
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7351
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7353
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7356
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7360
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7365
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7369
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7371
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7372
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7374
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7375
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7375
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7375
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7375
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7374
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7374
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7373
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7373
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7372
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7371
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7370
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7369
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7368
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7367
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7365
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7365 - val_accuracy: 0.3752 - val_loss: 1.7581
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.5463
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7038  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7126
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7209
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7290
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7349
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7380
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7396
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7399
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7393
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7378
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7366
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7361
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7358
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7358
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7358
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7357
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7356
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7355
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7354
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7353
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7351
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7348
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7344
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7342
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7341
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7338
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7335
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7332
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7328
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7325
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7323
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7320
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7318
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7316
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3662 - loss: 1.7314
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7312
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7310
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7308
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7305
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7303
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7300
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7298
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7295
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7293
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7292 - val_accuracy: 0.3941 - val_loss: 1.7611
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.0625 - loss: 2.4901
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7410  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7311
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7268
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7227
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7197
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7186
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7166
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3635 - loss: 1.7144
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7123
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3640 - loss: 1.7109
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7092
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7075
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7057
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7040
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7024
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7010
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7000
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3682 - loss: 1.6991
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.6984
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3685 - loss: 1.6978
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3687 - loss: 1.6974
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3688 - loss: 1.6970
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3689 - loss: 1.6966
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3690 - loss: 1.6963
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3690 - loss: 1.6960
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3691 - loss: 1.6957
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.6952
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3694 - loss: 1.6950
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3695 - loss: 1.6947
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3696 - loss: 1.6945
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3697 - loss: 1.6943
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3698 - loss: 1.6942
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3699 - loss: 1.6941
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3700 - loss: 1.6940
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3700 - loss: 1.6939
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3701 - loss: 1.6939
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3701 - loss: 1.6939
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3701 - loss: 1.6940
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3701 - loss: 1.6941
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3702 - loss: 1.6942
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3702 - loss: 1.6943
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3703 - loss: 1.6943
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3703 - loss: 1.6944 - val_accuracy: 0.3793 - val_loss: 1.7501
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.4833
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3855 - loss: 1.6557  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3872 - loss: 1.6617
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3871 - loss: 1.6717
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6726
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6724
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3856 - loss: 1.6731
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3854 - loss: 1.6733
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3850 - loss: 1.6742
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6750
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6761
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6766
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6771
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3841 - loss: 1.6772
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3837 - loss: 1.6776
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6781
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6785
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6790
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3813 - loss: 1.6794
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3808 - loss: 1.6796
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3805 - loss: 1.6797
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3802 - loss: 1.6798
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3799 - loss: 1.6799
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3797 - loss: 1.6799
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6799
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3793 - loss: 1.6799
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3792 - loss: 1.6799
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3791 - loss: 1.6799
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3791 - loss: 1.6798
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3792 - loss: 1.6797
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3792 - loss: 1.6796
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3793 - loss: 1.6795
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3793 - loss: 1.6795
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3794 - loss: 1.6795
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3794 - loss: 1.6794
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3794 - loss: 1.6794
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3794 - loss: 1.6793
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6793
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6792
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6792
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6792
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6792
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6793
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3796 - loss: 1.6793
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3796 - loss: 1.6793 - val_accuracy: 0.3759 - val_loss: 1.7706
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.5689
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3946 - loss: 1.6135  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4042 - loss: 1.6023
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4047 - loss: 1.5971
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4010 - loss: 1.5987
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3977 - loss: 1.6043
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6108
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3944 - loss: 1.6179
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3939 - loss: 1.6227
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6265
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6290
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3932 - loss: 1.6310
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6328
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3922 - loss: 1.6343
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6356
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3913 - loss: 1.6367
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3908 - loss: 1.6376
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3905 - loss: 1.6383
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3902 - loss: 1.6390
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3899 - loss: 1.6396
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3896 - loss: 1.6402
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3894 - loss: 1.6408
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3892 - loss: 1.6412
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3890 - loss: 1.6418
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3888 - loss: 1.6422
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3886 - loss: 1.6426
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3884 - loss: 1.6429
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3882 - loss: 1.6433
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3881 - loss: 1.6437
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3880 - loss: 1.6440
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6444
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3878 - loss: 1.6448
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3877 - loss: 1.6452
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3877 - loss: 1.6455
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6459
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6461
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6464
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6466
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6468
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6470
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6471
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6472
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6474
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6476
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6477
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6479
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6479 - val_accuracy: 0.3924 - val_loss: 1.7828

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 1s/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:47:54.053884: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:05[0m 1s/step
[1m 55/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 931us/step
[1m112/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 911us/step
[1m170/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 897us/step
[1m224/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 905us/step
[1m277/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 912us/step
[1m336/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 901us/step
[1m394/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 897us/step
[1m446/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 906us/step
[1m500/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 909us/step
[1m554/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 912us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 878us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 937us/step
[1m113/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 906us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 36.6 [%]
Global F1 score (validation) = 32.87 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.20955938 0.22090301 0.20201087 ... 0.01258098 0.13096826 0.03316139]
 [0.07076065 0.06556066 0.07520328 ... 0.05941057 0.0633592  0.13994929]
 [0.19798706 0.20956263 0.20441157 ... 0.0152326  0.13309938 0.04548628]
 ...
 [0.2117477  0.24203049 0.20360762 ... 0.00286395 0.14950456 0.01535553]
 [0.18848096 0.2033614  0.202327   ... 0.00144312 0.19131951 0.01428053]
 [0.21350558 0.22968689 0.21797723 ... 0.00397003 0.15187417 0.02194677]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 45.45 [%]
Global accuracy score (test) = 34.89 [%]
Global F1 score (train) = 41.28 [%]
Global F1 score (test) = 30.48 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.07      0.02      0.03       184
 CAMINAR CON MÓVIL O LIBRO       0.20      0.49      0.28       184
       CAMINAR USUAL SPEED       0.18      0.19      0.18       184
            CAMINAR ZIGZAG       0.53      0.54      0.53       184
          DE PIE BARRIENDO       0.30      0.37      0.33       184
   DE PIE DOBLANDO TOALLAS       0.34      0.06      0.10       184
    DE PIE MOVIENDO LIBROS       0.27      0.47      0.34       184
          DE PIE USANDO PC       0.49      0.65      0.56       184
        FASE REPOSO CON K5       0.80      0.64      0.71       184
INCREMENTAL CICLOERGOMETRO       0.67      0.55      0.60       184
           SENTADO LEYENDO       0.30      0.86      0.45       184
         SENTADO USANDO PC       0.20      0.01      0.02       184
      SENTADO VIENDO LA TV       0.00      0.00      0.00       184
   SUBIR Y BAJAR ESCALERAS       0.20      0.04      0.07       184
                    TROTAR       0.41      0.33      0.36       161

                  accuracy                           0.35      2737
                 macro avg       0.33      0.35      0.30      2737
              weighted avg       0.33      0.35      0.30      2737


Accuracy capturado en la ejecución 20: 34.89 [%]
F1-score capturado en la ejecución 20: 30.48 [%]

=== EJECUCIÓN 21 ===

--- TRAIN (ejecución 21) ---

--- TEST (ejecución 21) ---
2025-10-31 15:48:07.325473: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:48:07.336804: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761922087.350329 1710760 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761922087.354644 1710760 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761922087.364837 1710760 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922087.364861 1710760 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922087.364864 1710760 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922087.364865 1710760 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:48:07.368198: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761922089.745447 1710760 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761922092.836463 1710861 service.cc:152] XLA service 0x7f21b8003b40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761922092.836501 1710861 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:48:12.900456: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761922093.320110 1710861 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761922095.941098 1710861 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45:54[0m 5s/step - accuracy: 0.1250 - loss: 3.1460
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0593 - loss: 3.2894    
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0613 - loss: 3.3077
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0679 - loss: 3.2886
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0709 - loss: 3.2753
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0743 - loss: 3.2598
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0769 - loss: 3.2475
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0791 - loss: 3.2356
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0805 - loss: 3.2233
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0818 - loss: 3.2111
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0830 - loss: 3.1999
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0842 - loss: 3.1885
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0854 - loss: 3.1768
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0865 - loss: 3.1665
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0876 - loss: 3.1564
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0885 - loss: 3.1480
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0895 - loss: 3.1386
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0903 - loss: 3.1289
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0911 - loss: 3.1209
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0917 - loss: 3.1126
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0924 - loss: 3.1050
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0930 - loss: 3.0974
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0938 - loss: 3.0901
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0945 - loss: 3.0823
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0952 - loss: 3.0748
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0958 - loss: 3.0683
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0964 - loss: 3.0613
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0971 - loss: 3.0544
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0976 - loss: 3.0484
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0982 - loss: 3.0421
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0988 - loss: 3.0358
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0994 - loss: 3.0297
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0999 - loss: 3.0241
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1005 - loss: 3.0182
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1010 - loss: 3.0123
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1016 - loss: 3.0066
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1020 - loss: 3.0013
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1025 - loss: 2.9957
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1030 - loss: 2.9905
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1034 - loss: 2.9850
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1039 - loss: 2.9797
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1043 - loss: 2.9748
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1048 - loss: 2.9695
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1052 - loss: 2.9646
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1052 - loss: 2.9642
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1052 - loss: 2.9641 - val_accuracy: 0.1759 - val_loss: 2.2949
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.6012
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1770 - loss: 2.5444  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1702 - loss: 2.5261
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1627 - loss: 2.5255
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1577 - loss: 2.5241
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1548 - loss: 2.5218
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1534 - loss: 2.5196
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1526 - loss: 2.5176
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1524 - loss: 2.5149
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1523 - loss: 2.5127
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1521 - loss: 2.5104
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1520 - loss: 2.5086
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1520 - loss: 2.5066
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1521 - loss: 2.5043
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1524 - loss: 2.5021
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1526 - loss: 2.4998
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1528 - loss: 2.4976
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1531 - loss: 2.4952
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1533 - loss: 2.4933
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.4916
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1538 - loss: 2.4895
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1541 - loss: 2.4874
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1542 - loss: 2.4857
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1544 - loss: 2.4842
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1545 - loss: 2.4827
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1547 - loss: 2.4813
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1548 - loss: 2.4800
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1549 - loss: 2.4788
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1551 - loss: 2.4777
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1553 - loss: 2.4765
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4754
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1556 - loss: 2.4743
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1557 - loss: 2.4732
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1559 - loss: 2.4721
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1560 - loss: 2.4710
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1562 - loss: 2.4700
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1563 - loss: 2.4689
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1565 - loss: 2.4678
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1566 - loss: 2.4668
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1568 - loss: 2.4657
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1569 - loss: 2.4646
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1571 - loss: 2.4637
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1572 - loss: 2.4627
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4618
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4616 - val_accuracy: 0.2031 - val_loss: 2.1598
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.3680
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1620 - loss: 2.3785  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1747 - loss: 2.3830
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1766 - loss: 2.3834
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1758 - loss: 2.3812
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1756 - loss: 2.3771
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1753 - loss: 2.3749
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1756 - loss: 2.3730
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1758 - loss: 2.3711
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1761 - loss: 2.3688
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1764 - loss: 2.3661
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1765 - loss: 2.3647
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1766 - loss: 2.3627
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.3605
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1775 - loss: 2.3583
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.3562
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1782 - loss: 2.3543
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1785 - loss: 2.3525
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1787 - loss: 2.3507
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1789 - loss: 2.3490
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1791 - loss: 2.3476
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3459
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1794 - loss: 2.3445
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1795 - loss: 2.3429
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1796 - loss: 2.3416
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.3406
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.3396
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.3388
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.3381
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.3373
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3365
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3358
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3351
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3343
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3336
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3329
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3322
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3315
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3309
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3302
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3296
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3289
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3282
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3276
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3269
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1793 - loss: 2.3268 - val_accuracy: 0.2128 - val_loss: 2.0928
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.1250 - loss: 2.0127
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1639 - loss: 2.2625  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1716 - loss: 2.2909
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1774 - loss: 2.2908
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1830 - loss: 2.2839
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1861 - loss: 2.2793
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1887 - loss: 2.2745
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1910 - loss: 2.2710
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1927 - loss: 2.2685
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1938 - loss: 2.2652
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1945 - loss: 2.2630
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1950 - loss: 2.2612
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1953 - loss: 2.2594
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1957 - loss: 2.2574
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1962 - loss: 2.2560
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1966 - loss: 2.2552
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1970 - loss: 2.2546
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1974 - loss: 2.2537
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1977 - loss: 2.2530
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1979 - loss: 2.2523
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1982 - loss: 2.2516
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1984 - loss: 2.2510
[1m 593/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1985 - loss: 2.2505
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1986 - loss: 2.2501
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1987 - loss: 2.2499
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1987 - loss: 2.2496
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1987 - loss: 2.2494
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1986 - loss: 2.2491
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1986 - loss: 2.2488
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1986 - loss: 2.2485
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1986 - loss: 2.2482
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1986 - loss: 2.2478
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1985 - loss: 2.2474
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1985 - loss: 2.2471
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1984 - loss: 2.2468
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.2465
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1982 - loss: 2.2461
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1982 - loss: 2.2457
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1981 - loss: 2.2454
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1981 - loss: 2.2450
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1980 - loss: 2.2446
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1980 - loss: 2.2443
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1980 - loss: 2.2439
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1979 - loss: 2.2436
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1979 - loss: 2.2434 - val_accuracy: 0.2333 - val_loss: 2.0270
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2500 - loss: 2.1783
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2450 - loss: 2.1248  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2285 - loss: 2.1492
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2198 - loss: 2.1635
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2168 - loss: 2.1695
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2147 - loss: 2.1746
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2133 - loss: 2.1789
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.1810
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2114 - loss: 2.1824
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1834
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2111 - loss: 2.1834
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2108 - loss: 2.1838
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2103 - loss: 2.1841
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2100 - loss: 2.1843
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2098 - loss: 2.1845
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.1846
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2094 - loss: 2.1845
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2094 - loss: 2.1845
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2093 - loss: 2.1845
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2093 - loss: 2.1844
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2092 - loss: 2.1842
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2091 - loss: 2.1842
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2090 - loss: 2.1841
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2089 - loss: 2.1839
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2089 - loss: 2.1838
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1838
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2086 - loss: 2.1838
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2085 - loss: 2.1838
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2084 - loss: 2.1838
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2083 - loss: 2.1838
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.1838
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2081 - loss: 2.1837
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2080 - loss: 2.1837
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2079 - loss: 2.1836
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2078 - loss: 2.1835
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2077 - loss: 2.1835
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2076 - loss: 2.1835
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2076 - loss: 2.1834
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2076 - loss: 2.1834
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.1834
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.1833
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.1832
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.1831
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.1830
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.1829
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2075 - loss: 2.1828 - val_accuracy: 0.2488 - val_loss: 1.9892
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.1250 - loss: 2.1886
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2096 - loss: 2.1149  
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2121 - loss: 2.1207
[1m  69/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2123 - loss: 2.1272
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2148 - loss: 2.1329
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2151 - loss: 2.1382
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2146 - loss: 2.1426
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.1447
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.1467
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2148 - loss: 2.1481
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2150 - loss: 2.1488
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2154 - loss: 2.1490
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2158 - loss: 2.1486
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2163 - loss: 2.1481
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2166 - loss: 2.1476
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2168 - loss: 2.1471
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2170 - loss: 2.1468
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2172 - loss: 2.1463
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2174 - loss: 2.1457
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.1450
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2179 - loss: 2.1443
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2182 - loss: 2.1436
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1428
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2189 - loss: 2.1420
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.1412
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2196 - loss: 2.1403
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2200 - loss: 2.1395
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2203 - loss: 2.1387
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2207 - loss: 2.1379
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2211 - loss: 2.1371
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2214 - loss: 2.1363
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2218 - loss: 2.1355
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2221 - loss: 2.1348
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2224 - loss: 2.1343
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2227 - loss: 2.1337
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.1332
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2232 - loss: 2.1327
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2234 - loss: 2.1322
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1318
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2239 - loss: 2.1313
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1308
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2243 - loss: 2.1302
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.1297
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2248 - loss: 2.1292
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2250 - loss: 2.1287
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1283 - val_accuracy: 0.2546 - val_loss: 1.9667
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0269
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0611  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2992 - loss: 2.0612
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2955 - loss: 2.0628
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2909 - loss: 2.0659
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2880 - loss: 2.0673
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.0676
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2829 - loss: 2.0677
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 2.0691
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 2.0702
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.0705
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2755 - loss: 2.0705
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2739 - loss: 2.0706
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2727 - loss: 2.0708
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.0708
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2707 - loss: 2.0708
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2698 - loss: 2.0707
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2690 - loss: 2.0704
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2685 - loss: 2.0700
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2680 - loss: 2.0697
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.0694
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.0691
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2667 - loss: 2.0688
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2664 - loss: 2.0685
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.0680
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0678
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2655 - loss: 2.0676
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2653 - loss: 2.0673
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0671
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2648 - loss: 2.0670
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2646 - loss: 2.0668
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2644 - loss: 2.0665
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2643 - loss: 2.0663
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2641 - loss: 2.0661
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2640 - loss: 2.0659
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0657
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2637 - loss: 2.0654
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2636 - loss: 2.0651
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2635 - loss: 2.0648
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.0646
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0643
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2632 - loss: 2.0642
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0639
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0636
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0633
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0632 - val_accuracy: 0.3273 - val_loss: 1.8916
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.6653
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3210 - loss: 1.9561  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3000 - loss: 1.9867
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2933 - loss: 1.9907
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2897 - loss: 1.9940
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2875 - loss: 1.9961
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 1.9967
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 1.9969
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 1.9967
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9965
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2825 - loss: 1.9963
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 1.9963
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 1.9964
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9965
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9964
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9964
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9963
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2817 - loss: 1.9963
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 1.9966
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 1.9969
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9973
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9975
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2822 - loss: 1.9976
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 1.9977
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 1.9977
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 1.9977
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 1.9978
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 1.9978
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2826 - loss: 1.9978
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 1.9977
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 1.9976
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 1.9975
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9974
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9973
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9971
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9970
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 1.9969
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 1.9967
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9965
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9963
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9961
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9960
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9959
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 1.9958
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2833 - loss: 1.9958 - val_accuracy: 0.3277 - val_loss: 1.8706
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8496
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3452 - loss: 1.8732  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3242 - loss: 1.8920
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3170 - loss: 1.9032
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3132 - loss: 1.9092
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 1.9116
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 1.9131
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 1.9131
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 1.9126
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 1.9117
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9115
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 1.9119
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 1.9117
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 1.9115
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 1.9112
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 1.9111
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9111
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 1.9111
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.9111
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.9111
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 1.9111
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 1.9112
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 1.9116
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 1.9120
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 1.9123
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 1.9128
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 1.9131
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 1.9132
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 1.9135
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 1.9137
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 1.9140
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.9142
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 1.9145
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 1.9148
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 1.9151
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 1.9154
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3106 - loss: 1.9157
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3105 - loss: 1.9159
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 1.9161
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 1.9164
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3101 - loss: 1.9165
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3100 - loss: 1.9167
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 1.9170
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 1.9172
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3097 - loss: 1.9173 - val_accuracy: 0.2986 - val_loss: 1.8926
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.6970
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3052 - loss: 1.8765  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3098 - loss: 1.8905
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8880
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8868
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3104 - loss: 1.8884
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3099 - loss: 1.8888
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 1.8890
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 1.8887
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8884
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8886
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3121 - loss: 1.8888
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 1.8884
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 1.8877
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 1.8873
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 1.8869
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 1.8869
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 1.8868
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 1.8867
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 1.8864
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 1.8860
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 1.8856
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3159 - loss: 1.8851
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3162 - loss: 1.8848
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 1.8846
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8846
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8847
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8847
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8849
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8851
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8854
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8857
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 1.8858
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8859
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8859
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8860
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 1.8860
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8861
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8861
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8861
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8861
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8861
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 1.8861
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 1.8861
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8862 - val_accuracy: 0.3228 - val_loss: 1.8786
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.7338
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3446 - loss: 1.8221  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8404
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3253 - loss: 1.8473
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 1.8484
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3210 - loss: 1.8496
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 1.8505
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 1.8511
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8517
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3172 - loss: 1.8528
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8532
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 1.8532
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 1.8525
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8519
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8515
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8512
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8514
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8515
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8517
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8520
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8523
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8526
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8528
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 1.8529
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3181 - loss: 1.8528
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3184 - loss: 1.8527
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3186 - loss: 1.8526
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8526
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8527
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8528
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 1.8529
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8530
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 1.8530
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8530
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 1.8530
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 1.8531
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8532
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8534
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8535
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 1.8536
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 1.8536
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 1.8536
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 1.8536
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 1.8536
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 1.8536
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3208 - loss: 1.8536 - val_accuracy: 0.3580 - val_loss: 1.7676
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9611
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7753  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7836
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3504 - loss: 1.7960
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3458 - loss: 1.8009
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3448 - loss: 1.8025
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3443 - loss: 1.8030
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.8047
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3435 - loss: 1.8067
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3434 - loss: 1.8086
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.8102
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.8114
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3434 - loss: 1.8123
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.8137
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 1.8152
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3430 - loss: 1.8169
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8186
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8199
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3424 - loss: 1.8209
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3424 - loss: 1.8218
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3423 - loss: 1.8226
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3423 - loss: 1.8232
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3423 - loss: 1.8236
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3424 - loss: 1.8240
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3424 - loss: 1.8244
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8247
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8250
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8251
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.8253
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3430 - loss: 1.8255
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3431 - loss: 1.8256
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3432 - loss: 1.8257
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.8258
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3434 - loss: 1.8259
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3435 - loss: 1.8258
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3436 - loss: 1.8258
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3437 - loss: 1.8258
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3438 - loss: 1.8257
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3439 - loss: 1.8256
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3440 - loss: 1.8255
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3441 - loss: 1.8254
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3442 - loss: 1.8252
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3442 - loss: 1.8252
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3442 - loss: 1.8251
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3442 - loss: 1.8251 - val_accuracy: 0.3271 - val_loss: 1.8330
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8843
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8896  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3104 - loss: 1.8608
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3144 - loss: 1.8363
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3183 - loss: 1.8245
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3199 - loss: 1.8207
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 1.8157
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8118
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3260 - loss: 1.8090
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3276 - loss: 1.8070
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8052
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8035
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3308 - loss: 1.8021
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8009
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3324 - loss: 1.7998
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 1.7989
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 1.7981
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3343 - loss: 1.7976
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3349 - loss: 1.7972
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 1.7969
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3360 - loss: 1.7967
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3365 - loss: 1.7965
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3370 - loss: 1.7967
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3373 - loss: 1.7969
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3376 - loss: 1.7970
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.7970
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 1.7969
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3385 - loss: 1.7969
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3388 - loss: 1.7968
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.7968
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.7967
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.7966
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.7965
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.7964
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.7963
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.7962
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3406 - loss: 1.7962
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3408 - loss: 1.7962
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 1.7962
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7962
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3413 - loss: 1.7963
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3414 - loss: 1.7963
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3415 - loss: 1.7964
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.7964
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3417 - loss: 1.7964 - val_accuracy: 0.3463 - val_loss: 1.7835
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.8227
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2865 - loss: 1.8232  
[1m  57/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3132 - loss: 1.7919
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3264 - loss: 1.7853
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3328 - loss: 1.7878
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3372 - loss: 1.7876
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 1.7857
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3425 - loss: 1.7846
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3445 - loss: 1.7834
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3459 - loss: 1.7826
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3472 - loss: 1.7820
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7817
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3488 - loss: 1.7813
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7808
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7807
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7805
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7804
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3505 - loss: 1.7801
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3508 - loss: 1.7799
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3511 - loss: 1.7797
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3514 - loss: 1.7797
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3516 - loss: 1.7798
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7799
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3521 - loss: 1.7799
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3522 - loss: 1.7801
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7803
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3525 - loss: 1.7806
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3527 - loss: 1.7807
[1m 756/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3528 - loss: 1.7808
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7809
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3530 - loss: 1.7811
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3531 - loss: 1.7812
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3532 - loss: 1.7813
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7814
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7815
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7815
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7815
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7815
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7815
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7815
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7815
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7815
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7815
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7815
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7815 - val_accuracy: 0.3486 - val_loss: 1.8005
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8758
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3216 - loss: 1.8212  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3391 - loss: 1.7823
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3439 - loss: 1.7853
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7831
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3528 - loss: 1.7829
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7841
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7839
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7840
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7838
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7835
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7834
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7838
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7841
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7845
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7848
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7849
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7850
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7849
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7847
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7844
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7841
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7838
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7835
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7831
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7828
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7825
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7821
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7817
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7812
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7807
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7801
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7796
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7791
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7786
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7781
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7776
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7772
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7768
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7763
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7759
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7755
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7751
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7747
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7744
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7743 - val_accuracy: 0.3856 - val_loss: 1.7461
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 1.6932
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3972 - loss: 1.6013  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3911 - loss: 1.6320
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3885 - loss: 1.6454
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3872 - loss: 1.6566
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3861 - loss: 1.6659
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6731
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3837 - loss: 1.6799
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3823 - loss: 1.6858
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3813 - loss: 1.6898
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3803 - loss: 1.6934
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3792 - loss: 1.6957
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.6979
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3778 - loss: 1.6997
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7017
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3764 - loss: 1.7037
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3757 - loss: 1.7057
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7071
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3746 - loss: 1.7081
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7091
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3739 - loss: 1.7101
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3736 - loss: 1.7113
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7124
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7134
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7145
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3726 - loss: 1.7155
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7164
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7171
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7176
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7181
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7186
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7190
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7195
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7199
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7203
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7206
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7209
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7212
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7215
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7218
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7221
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7223
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7225
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7228
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7230 - val_accuracy: 0.3776 - val_loss: 1.7395
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 2.3167
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3755 - loss: 1.8279  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3700 - loss: 1.8015
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7795
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3692 - loss: 1.7635
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7534
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7464
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7430
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7403
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7373
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3727 - loss: 1.7348
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3733 - loss: 1.7329
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7313
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7301
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7288
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3734 - loss: 1.7277
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7264
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3736 - loss: 1.7251
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3738 - loss: 1.7239
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3740 - loss: 1.7227
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7214
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3742 - loss: 1.7206
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3742 - loss: 1.7199
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3742 - loss: 1.7195
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3742 - loss: 1.7191
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3742 - loss: 1.7187
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7184
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7182
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7180
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3740 - loss: 1.7180
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7179
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7177
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7176
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3742 - loss: 1.7174
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7172
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3744 - loss: 1.7170
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3745 - loss: 1.7168
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3746 - loss: 1.7166
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3746 - loss: 1.7163
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3746 - loss: 1.7161
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3747 - loss: 1.7159
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3747 - loss: 1.7158
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3747 - loss: 1.7157
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3747 - loss: 1.7155
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3747 - loss: 1.7154 - val_accuracy: 0.3663 - val_loss: 1.7682
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.4986
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7395  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3662 - loss: 1.7284
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7124
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3737 - loss: 1.7066
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7055
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7061
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3750 - loss: 1.7046
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7029
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7017
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7005
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.6997
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.6991
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3789 - loss: 1.6986
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3796 - loss: 1.6978
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3801 - loss: 1.6969
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3805 - loss: 1.6962
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3808 - loss: 1.6956
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3811 - loss: 1.6951
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3814 - loss: 1.6946
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3817 - loss: 1.6942
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6939
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6936
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3824 - loss: 1.6932
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6929
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3828 - loss: 1.6925
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6921
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3833 - loss: 1.6916
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6912
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3837 - loss: 1.6907
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3839 - loss: 1.6902
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3841 - loss: 1.6899
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6896
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6893
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6891
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3848 - loss: 1.6889
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3850 - loss: 1.6886
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3851 - loss: 1.6884
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3853 - loss: 1.6881
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.6879
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3855 - loss: 1.6877
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3856 - loss: 1.6876
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3856 - loss: 1.6875
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3857 - loss: 1.6874
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3857 - loss: 1.6874 - val_accuracy: 0.3621 - val_loss: 1.8088
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.4375 - loss: 1.2548
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3492 - loss: 1.6187  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3604 - loss: 1.6391
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3674 - loss: 1.6471
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3724 - loss: 1.6530
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3757 - loss: 1.6560
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.6559
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3813 - loss: 1.6541
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3828 - loss: 1.6539
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3837 - loss: 1.6540
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6535
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3857 - loss: 1.6531
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3863 - loss: 1.6533
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6538
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6544
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3868 - loss: 1.6549
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6553
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3871 - loss: 1.6556
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3871 - loss: 1.6559
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6564
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6569
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3868 - loss: 1.6575
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6582
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6588
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3866 - loss: 1.6594
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3866 - loss: 1.6598
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6600
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3864 - loss: 1.6602
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3863 - loss: 1.6605
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3863 - loss: 1.6609
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3862 - loss: 1.6612
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3861 - loss: 1.6615
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3861 - loss: 1.6618
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6621
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6623
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6625
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6627
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6629
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6630
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6633
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6635
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6636
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6638
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6640
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6641
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6641 - val_accuracy: 0.3632 - val_loss: 1.7919
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 1.6285
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3543 - loss: 1.6826  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3696 - loss: 1.6805
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6733
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6642
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6583
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3896 - loss: 1.6536
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3904 - loss: 1.6519
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3911 - loss: 1.6517
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3925 - loss: 1.6511
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6506
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3942 - loss: 1.6496
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3948 - loss: 1.6489
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3952 - loss: 1.6483
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3956 - loss: 1.6479
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6473
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3965 - loss: 1.6468
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6464
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6462
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3974 - loss: 1.6460
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3975 - loss: 1.6461
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3975 - loss: 1.6462
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3975 - loss: 1.6464
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3974 - loss: 1.6466
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3974 - loss: 1.6468
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3973 - loss: 1.6471
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3972 - loss: 1.6473
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3972 - loss: 1.6475
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6478
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6480
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6482
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6483
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6483
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6483
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6483
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6484
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6485
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6486
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6488
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6489
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6491
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6493
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6495
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6497
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6499
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6499 - val_accuracy: 0.3809 - val_loss: 1.7728
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 1.6597
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4141 - loss: 1.6485  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3985 - loss: 1.6468
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6392
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3913 - loss: 1.6372
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3920 - loss: 1.6341
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6343
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3916 - loss: 1.6352
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6351
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6343
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6334
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6327
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6319
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6312
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6308
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6306
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6304
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6305
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6305
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6305
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6306
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6307
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6308
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6308
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6310
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6311
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6313
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6314
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6316
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3916 - loss: 1.6317
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3916 - loss: 1.6318
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3915 - loss: 1.6319
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3915 - loss: 1.6320
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3914 - loss: 1.6321
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3914 - loss: 1.6321
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3915 - loss: 1.6322
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3915 - loss: 1.6323
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3915 - loss: 1.6324
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3916 - loss: 1.6325
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3916 - loss: 1.6326
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6327
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6328
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6329
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3919 - loss: 1.6330
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3919 - loss: 1.6330
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3919 - loss: 1.6330 - val_accuracy: 0.3852 - val_loss: 1.7735

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 1s/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:49:19.689164: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:35[0m 1s/step
[1m 52/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 990us/step
[1m111/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 918us/step
[1m164/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 928us/step
[1m224/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 905us/step
[1m272/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 931us/step
[1m325/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 935us/step
[1m381/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 929us/step
[1m440/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 920us/step
[1m496/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 918us/step
[1m553/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 914us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 987us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 981us/step
[1m106/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 969us/step
[1m153/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 39.24 [%]
Global F1 score (validation) = 37.64 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.22520392 0.21395257 0.1993357  ... 0.00418534 0.16573079 0.01447607]
 [0.10318767 0.13425104 0.10167636 ... 0.0296252  0.11998791 0.13563363]
 [0.22248107 0.21014696 0.205361   ... 0.00277669 0.18158367 0.01260665]
 ...
 [0.2076469  0.15043914 0.17742808 ... 0.00096749 0.22128929 0.08878256]
 [0.21985486 0.21020894 0.2029457  ... 0.00351789 0.18690915 0.02910318]
 [0.08201276 0.10935785 0.07974302 ... 0.01259847 0.05305829 0.00839882]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.36 [%]
Global accuracy score (test) = 33.76 [%]
Global F1 score (train) = 44.44 [%]
Global F1 score (test) = 32.03 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.20      0.42      0.27       184
 CAMINAR CON MÓVIL O LIBRO       0.26      0.23      0.25       184
       CAMINAR USUAL SPEED       0.14      0.02      0.03       184
            CAMINAR ZIGZAG       0.49      0.48      0.49       184
          DE PIE BARRIENDO       0.29      0.41      0.34       184
   DE PIE DOBLANDO TOALLAS       0.43      0.21      0.28       184
    DE PIE MOVIENDO LIBROS       0.28      0.40      0.33       184
          DE PIE USANDO PC       0.28      0.72      0.41       184
        FASE REPOSO CON K5       0.74      0.55      0.63       184
INCREMENTAL CICLOERGOMETRO       0.66      0.51      0.57       184
           SENTADO LEYENDO       0.27      0.31      0.29       184
         SENTADO USANDO PC       0.18      0.06      0.09       184
      SENTADO VIENDO LA TV       0.50      0.14      0.22       184
   SUBIR Y BAJAR ESCALERAS       0.29      0.15      0.19       184
                    TROTAR       0.38      0.47      0.42       161

                  accuracy                           0.34      2737
                 macro avg       0.36      0.34      0.32      2737
              weighted avg       0.36      0.34      0.32      2737


Accuracy capturado en la ejecución 21: 33.76 [%]
F1-score capturado en la ejecución 21: 32.03 [%]

=== EJECUCIÓN 22 ===

--- TRAIN (ejecución 22) ---

--- TEST (ejecución 22) ---
2025-10-31 15:49:32.857261: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:49:32.868509: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761922172.881746 1714241 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761922172.885877 1714241 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761922172.895549 1714241 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922172.895570 1714241 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922172.895572 1714241 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922172.895574 1714241 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:49:32.898706: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761922175.249800 1714241 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761922178.330550 1714338 service.cc:152] XLA service 0x7d35bc01ab80 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761922178.330589 1714338 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:49:38.394506: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761922178.812536 1714338 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761922181.439509 1714338 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45:39[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.5494
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0367 - loss: 3.4126        
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0468 - loss: 3.3772
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0531 - loss: 3.3475
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0572 - loss: 3.3254
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0606 - loss: 3.3055
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0638 - loss: 3.2895
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0666 - loss: 3.2765
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0689 - loss: 3.2661
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0711 - loss: 3.2534
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0729 - loss: 3.2409
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0745 - loss: 3.2295
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0763 - loss: 3.2175
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0779 - loss: 3.2064
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0795 - loss: 3.1950
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0810 - loss: 3.1845
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0823 - loss: 3.1743
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0835 - loss: 3.1646
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0847 - loss: 3.1552
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0857 - loss: 3.1475
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0868 - loss: 3.1392
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0877 - loss: 3.1312
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0886 - loss: 3.1231
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0894 - loss: 3.1161
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0903 - loss: 3.1085
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0910 - loss: 3.1015
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0918 - loss: 3.0949
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0924 - loss: 3.0885
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0932 - loss: 3.0814
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0940 - loss: 3.0747
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0947 - loss: 3.0685
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0954 - loss: 3.0621
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0961 - loss: 3.0559
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0967 - loss: 3.0509
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0973 - loss: 3.0450
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0980 - loss: 3.0391
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0986 - loss: 3.0334
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0992 - loss: 3.0281
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0998 - loss: 3.0222
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1004 - loss: 3.0171
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1009 - loss: 3.0119
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1014 - loss: 3.0073
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1020 - loss: 3.0020
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1025 - loss: 2.9971
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1028 - loss: 2.9934
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1029 - loss: 2.9931
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1029 - loss: 2.9929 - val_accuracy: 0.1822 - val_loss: 2.2658
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.4375 - loss: 1.8767
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1878 - loss: 2.3712  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1635 - loss: 2.4348
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1573 - loss: 2.4607
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1540 - loss: 2.4823
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1518 - loss: 2.4939
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1506 - loss: 2.5016
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1498 - loss: 2.5054
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1492 - loss: 2.5069
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1489 - loss: 2.5078
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1486 - loss: 2.5081
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1484 - loss: 2.5082
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1481 - loss: 2.5080
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1477 - loss: 2.5077
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1475 - loss: 2.5076
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1472 - loss: 2.5072
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1471 - loss: 2.5068
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1471 - loss: 2.5065
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1472 - loss: 2.5061
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1472 - loss: 2.5056
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1473 - loss: 2.5049
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1474 - loss: 2.5043
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1475 - loss: 2.5035
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1476 - loss: 2.5026
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1477 - loss: 2.5018
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1478 - loss: 2.5009
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1480 - loss: 2.4999
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1482 - loss: 2.4990
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1484 - loss: 2.4980
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1485 - loss: 2.4972
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1486 - loss: 2.4964
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1488 - loss: 2.4955
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1489 - loss: 2.4947
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1490 - loss: 2.4938
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1491 - loss: 2.4930
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1492 - loss: 2.4920
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1494 - loss: 2.4910
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1495 - loss: 2.4901
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1497 - loss: 2.4891
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1499 - loss: 2.4882
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1500 - loss: 2.4873
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1502 - loss: 2.4864
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1504 - loss: 2.4856
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1505 - loss: 2.4848
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1506 - loss: 2.4840
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1507 - loss: 2.4837 - val_accuracy: 0.2002 - val_loss: 2.1590
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.0153
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2037 - loss: 2.2661  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1871 - loss: 2.2908
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1802 - loss: 2.3061
[1m 113/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1776 - loss: 2.3126
[1m 141/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1761 - loss: 2.3159
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1751 - loss: 2.3192
[1m 194/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1748 - loss: 2.3223
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1748 - loss: 2.3244
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1745 - loss: 2.3272
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1743 - loss: 2.3294
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1742 - loss: 2.3304
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1742 - loss: 2.3309
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1742 - loss: 2.3316
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1742 - loss: 2.3323
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1742 - loss: 2.3328
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1741 - loss: 2.3333
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1740 - loss: 2.3337
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1739 - loss: 2.3340
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1739 - loss: 2.3344
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1738 - loss: 2.3347
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1737 - loss: 2.3349
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1736 - loss: 2.3350
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1735 - loss: 2.3352
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.3353
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1734 - loss: 2.3353
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1733 - loss: 2.3353
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1732 - loss: 2.3352
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1731 - loss: 2.3352
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1731 - loss: 2.3351
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1731 - loss: 2.3350
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1731 - loss: 2.3349
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1731 - loss: 2.3349
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1730 - loss: 2.3348
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1730 - loss: 2.3348
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1730 - loss: 2.3348
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1729 - loss: 2.3348
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1729 - loss: 2.3348
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1729 - loss: 2.3347
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1729 - loss: 2.3346
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1729 - loss: 2.3345
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1729 - loss: 2.3344
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1728 - loss: 2.3343
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1728 - loss: 2.3342
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1728 - loss: 2.3341
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1728 - loss: 2.3341 - val_accuracy: 0.2183 - val_loss: 2.0979
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4355
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1723 - loss: 2.3606  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3314
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1690 - loss: 2.3247
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1724 - loss: 2.3189
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1749 - loss: 2.3131
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1761 - loss: 2.3089
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1766 - loss: 2.3054
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1769 - loss: 2.3027
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.3011
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.3003
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1769 - loss: 2.2997
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1770 - loss: 2.2987
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1772 - loss: 2.2977
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.2964
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.2953
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.2947
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1772 - loss: 2.2940
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1770 - loss: 2.2935
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1767 - loss: 2.2930
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1765 - loss: 2.2926
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1763 - loss: 2.2922
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1762 - loss: 2.2919
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1761 - loss: 2.2915
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2909
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2904
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2899
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2894
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2888
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2884
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1760 - loss: 2.2881
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1759 - loss: 2.2877
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1759 - loss: 2.2873
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1758 - loss: 2.2869
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1758 - loss: 2.2866
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1757 - loss: 2.2862
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1757 - loss: 2.2858
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1757 - loss: 2.2853
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1756 - loss: 2.2849
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1756 - loss: 2.2844
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1756 - loss: 2.2839
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1756 - loss: 2.2835
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1756 - loss: 2.2830
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1756 - loss: 2.2826
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1757 - loss: 2.2821
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1757 - loss: 2.2818 - val_accuracy: 0.2242 - val_loss: 2.0609
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.1245
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1993 - loss: 2.1802  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1951 - loss: 2.2073
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1981 - loss: 2.2121
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1992 - loss: 2.2159
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1995 - loss: 2.2204
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1996 - loss: 2.2236
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1995 - loss: 2.2261
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1993 - loss: 2.2271
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1998 - loss: 2.2263
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2001 - loss: 2.2251
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2001 - loss: 2.2239
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2001 - loss: 2.2230
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2001 - loss: 2.2225
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2003 - loss: 2.2217
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2004 - loss: 2.2213
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2005 - loss: 2.2208
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2006 - loss: 2.2204
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2008 - loss: 2.2198
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2194
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.2190
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.2187
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.2184
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2182
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2179
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2176
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2172
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2168
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2164
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2009 - loss: 2.2159
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.2155
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.2150
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.2147
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.2143
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.2140
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.2136
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.2134
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.2131
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.2128
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.2126
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.2123
[1m1078/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.2121
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.2119
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2012 - loss: 2.2117
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2012 - loss: 2.2114
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2012 - loss: 2.2113 - val_accuracy: 0.2788 - val_loss: 2.0114
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2500 - loss: 1.7876
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2084 - loss: 2.1137  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2081 - loss: 2.1408
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2066 - loss: 2.1544
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2069 - loss: 2.1599
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2069 - loss: 2.1609
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2064 - loss: 2.1630
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2057 - loss: 2.1657
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2053 - loss: 2.1681
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2054 - loss: 2.1699
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2059 - loss: 2.1709
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2062 - loss: 2.1716
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2063 - loss: 2.1718
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2067 - loss: 2.1717
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2073 - loss: 2.1710
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2079 - loss: 2.1701
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2083 - loss: 2.1695
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2087 - loss: 2.1689
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2091 - loss: 2.1683
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.1675
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2100 - loss: 2.1668
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2103 - loss: 2.1661
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2106 - loss: 2.1654
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2109 - loss: 2.1649
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2111 - loss: 2.1643
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2112 - loss: 2.1638
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2114 - loss: 2.1633
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2115 - loss: 2.1629
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2117 - loss: 2.1625
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2118 - loss: 2.1621
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2120 - loss: 2.1618
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2121 - loss: 2.1615
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2123 - loss: 2.1612
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2124 - loss: 2.1610
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2125 - loss: 2.1608
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2127 - loss: 2.1607
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2127 - loss: 2.1605
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2128 - loss: 2.1604
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2129 - loss: 2.1603
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.1601
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.1600
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.1600
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.1600
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2133 - loss: 2.1599
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2134 - loss: 2.1598
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2135 - loss: 2.1597
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2135 - loss: 2.1597 - val_accuracy: 0.2905 - val_loss: 1.9677
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2500 - loss: 2.1327
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2004 - loss: 2.1722  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2138 - loss: 2.1420
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2184 - loss: 2.1275
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2204 - loss: 2.1216
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2215 - loss: 2.1176
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2216 - loss: 2.1166
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2216 - loss: 2.1169
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2218 - loss: 2.1163
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2217 - loss: 2.1167
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2217 - loss: 2.1173
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2220 - loss: 2.1176
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2223 - loss: 2.1178
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2228 - loss: 2.1179
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2231 - loss: 2.1177
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2234 - loss: 2.1176
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1177
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2238 - loss: 2.1175
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2242 - loss: 2.1171
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2245 - loss: 2.1167
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2249 - loss: 2.1163
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1157
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2256 - loss: 2.1151
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2260 - loss: 2.1146
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2264 - loss: 2.1142
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2268 - loss: 2.1138
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2271 - loss: 2.1134
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2273 - loss: 2.1130
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2276 - loss: 2.1126
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2279 - loss: 2.1123
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2281 - loss: 2.1120
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2283 - loss: 2.1116
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2285 - loss: 2.1113
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2287 - loss: 2.1110
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2289 - loss: 2.1106
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2291 - loss: 2.1103
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2293 - loss: 2.1099
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2295 - loss: 2.1096
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2297 - loss: 2.1093
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2299 - loss: 2.1090
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2301 - loss: 2.1087
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2303 - loss: 2.1084
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2305 - loss: 2.1082
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2307 - loss: 2.1079
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2308 - loss: 2.1076
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2309 - loss: 2.1075 - val_accuracy: 0.2638 - val_loss: 1.9426
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3643
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2261 - loss: 2.1112  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2423 - loss: 2.0538
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2506 - loss: 2.0359
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2558 - loss: 2.0268
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.0245
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2579 - loss: 2.0246
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2585 - loss: 2.0263
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2585 - loss: 2.0289
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2581 - loss: 2.0309
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2577 - loss: 2.0330
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2576 - loss: 2.0343
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2575 - loss: 2.0355
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2574 - loss: 2.0366
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2574 - loss: 2.0378
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2574 - loss: 2.0387
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.0397
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.0405
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2572 - loss: 2.0414
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.0423
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.0433
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.0441
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.0449
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.0457
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.0464
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2571 - loss: 2.0471
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2571 - loss: 2.0476
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2572 - loss: 2.0481
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2573 - loss: 2.0486
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2574 - loss: 2.0489
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.0493
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2576 - loss: 2.0497
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.0501
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2578 - loss: 2.0503
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2578 - loss: 2.0506
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.0508
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.0510
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2580 - loss: 2.0511
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2580 - loss: 2.0513
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2581 - loss: 2.0513
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2581 - loss: 2.0514
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.0515
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2583 - loss: 2.0515
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.0515
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.0514
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2585 - loss: 2.0514 - val_accuracy: 0.3362 - val_loss: 1.9025
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8074
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2574 - loss: 1.9783  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2487 - loss: 1.9951
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2489 - loss: 2.0097
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2501 - loss: 2.0168
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2518 - loss: 2.0179
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2537 - loss: 2.0182
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2556 - loss: 2.0173
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.0166
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2584 - loss: 2.0165
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2591 - loss: 2.0168
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.0165
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2605 - loss: 2.0158
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2610 - loss: 2.0155
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.0157
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0164
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2622 - loss: 2.0172
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2626 - loss: 2.0180
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0189
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2632 - loss: 2.0193
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 2.0197
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2639 - loss: 2.0198
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2643 - loss: 2.0197
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2646 - loss: 2.0196
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0194
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2653 - loss: 2.0193
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2657 - loss: 2.0190
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0188
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2664 - loss: 2.0185
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2668 - loss: 2.0182
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2671 - loss: 2.0178
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2674 - loss: 2.0175
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2677 - loss: 2.0172
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2679 - loss: 2.0168
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.0164
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.0160
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2688 - loss: 2.0158
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2690 - loss: 2.0155
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2692 - loss: 2.0153
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2693 - loss: 2.0151
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.0148
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2696 - loss: 2.0146
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.0143
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.0141
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.0138
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2703 - loss: 2.0135 - val_accuracy: 0.3456 - val_loss: 1.8531
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.4375 - loss: 1.7084
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2759 - loss: 1.9312  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2835 - loss: 1.9199
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2878 - loss: 1.9134
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2907 - loss: 1.9158
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2922 - loss: 1.9192
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2929 - loss: 1.9231
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2931 - loss: 1.9264
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 1.9290
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9299
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9310
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2978 - loss: 1.9316
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9323
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 1.9330
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 1.9339
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 1.9344
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 1.9349
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 1.9356
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 1.9361
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 1.9366
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9373
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 1.9380
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9388
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9396
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9405
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9412
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9418
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9425
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9431
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9436
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9441
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9446
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9450
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9454
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9456
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9459
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 1.9461
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 1.9463
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 1.9465
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 1.9467
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 1.9469
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 1.9470
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 1.9471
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 1.9472
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 1.9473
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 1.9474
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3010 - loss: 1.9475 - val_accuracy: 0.3628 - val_loss: 1.8180
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.1410
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3307 - loss: 1.8711  
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3249 - loss: 1.8688
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3238 - loss: 1.8748
[1m  96/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3227 - loss: 1.8800
[1m 122/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3232 - loss: 1.8850
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3229 - loss: 1.8889
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3219 - loss: 1.8930
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 1.8962
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8990
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 1.9010
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 1.9021
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3186 - loss: 1.9036
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3181 - loss: 1.9046
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3177 - loss: 1.9056
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3172 - loss: 1.9063
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 1.9069
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3162 - loss: 1.9079
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 1.9086
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 1.9092
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 1.9096
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 1.9100
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 1.9105
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 1.9110
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 1.9114
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 1.9117
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 1.9120
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3146 - loss: 1.9124
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3144 - loss: 1.9128
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3143 - loss: 1.9133
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3141 - loss: 1.9136
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3141 - loss: 1.9140
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 1.9143
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3139 - loss: 1.9144
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 1.9146
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9148
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9150
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9150
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3136 - loss: 1.9150
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9151
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9150
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9151
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9151
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9150
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9150
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9150
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9149 - val_accuracy: 0.3439 - val_loss: 1.8115
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8797
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3555 - loss: 1.8507  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3468 - loss: 1.8524
[1m  84/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3434 - loss: 1.8489
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8520
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3373 - loss: 1.8539
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 1.8541
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8546
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3341 - loss: 1.8558
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8560
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3341 - loss: 1.8569
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8580
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8591
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 1.8599
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8609
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3330 - loss: 1.8618
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3328 - loss: 1.8625
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3326 - loss: 1.8632
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.8637
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3324 - loss: 1.8641
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3322 - loss: 1.8645
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 1.8648
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 1.8652
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8655
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8657
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8659
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3314 - loss: 1.8661
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8663
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8666
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3309 - loss: 1.8669
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 1.8671
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8674
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 1.8677
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8680
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 1.8682
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8683
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3298 - loss: 1.8684
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3296 - loss: 1.8685
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3296 - loss: 1.8684
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8684
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8683
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8681
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8680
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3294 - loss: 1.8678
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3294 - loss: 1.8676 - val_accuracy: 0.3600 - val_loss: 1.7956
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5625 - loss: 1.5726
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3473 - loss: 1.9762  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3340 - loss: 1.9732
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3365 - loss: 1.9581
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9455
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.9334
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3441 - loss: 1.9255
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3453 - loss: 1.9193
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3457 - loss: 1.9139
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3455 - loss: 1.9098
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3453 - loss: 1.9062
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.9021
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3450 - loss: 1.8984
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3448 - loss: 1.8949
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3447 - loss: 1.8922
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3445 - loss: 1.8899
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3442 - loss: 1.8885
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.8873
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 1.8861
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3434 - loss: 1.8851
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 1.8843
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3430 - loss: 1.8832
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8822
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8814
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8806
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3422 - loss: 1.8799
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3420 - loss: 1.8792
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8785
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8779
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3412 - loss: 1.8773
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8767
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3408 - loss: 1.8760
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3406 - loss: 1.8754
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.8748
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8743
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8737
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8731
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8726
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8720
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8715
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8709
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8702
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8696
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8690
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8686 - val_accuracy: 0.3684 - val_loss: 1.7761
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0498
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3406 - loss: 1.9666  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3476 - loss: 1.8832
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3503 - loss: 1.8516
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3523 - loss: 1.8266
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3534 - loss: 1.8149
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3535 - loss: 1.8083
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3540 - loss: 1.8024
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3541 - loss: 1.7988
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7973
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7974
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3531 - loss: 1.7981
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7992
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3517 - loss: 1.8002
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3513 - loss: 1.8011
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3508 - loss: 1.8023
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3503 - loss: 1.8036
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.8046
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.8056
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3494 - loss: 1.8063
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8069
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3489 - loss: 1.8074
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8078
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8081
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8083
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8083
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8084
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8085
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3487 - loss: 1.8086
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8087
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8087
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8087
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3485 - loss: 1.8087
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3485 - loss: 1.8088
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3485 - loss: 1.8088
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3485 - loss: 1.8088
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3485 - loss: 1.8088
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3485 - loss: 1.8088
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8088
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3486 - loss: 1.8087
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3487 - loss: 1.8087
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3487 - loss: 1.8086
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8085
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8084
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3488 - loss: 1.8084
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3489 - loss: 1.8083 - val_accuracy: 0.3671 - val_loss: 1.7588
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0390
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7499  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3617 - loss: 1.7457
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7474
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7503
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7537
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7547
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7539
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7535
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7543
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7547
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7549
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7551
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7557
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7567
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7575
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7582
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7591
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7601
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7611
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7618
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7627
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7635
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7642
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7647
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7651
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7656
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7661
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7666
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7670
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7675
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3617 - loss: 1.7679
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7683
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7686
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7689
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7692
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7695
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7698
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7700
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7702
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7704
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7705
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7707
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7708
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7710
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7710 - val_accuracy: 0.3591 - val_loss: 1.7452
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.4375 - loss: 1.4402
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7201  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3436 - loss: 1.7510
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3446 - loss: 1.7570
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3439 - loss: 1.7641
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3426 - loss: 1.7682
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3424 - loss: 1.7692
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3427 - loss: 1.7694
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3438 - loss: 1.7684
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.7673
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.7667
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7666
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3488 - loss: 1.7663
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7661
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7661
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3509 - loss: 1.7661
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3514 - loss: 1.7658
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7654
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7648
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3528 - loss: 1.7642
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7636
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7631
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7626
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7622
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7618
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7614
[1m 676/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7611
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7608
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3556 - loss: 1.7605
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3559 - loss: 1.7602
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7599
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7596
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7593
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7591
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7589
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7587
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7585
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7583
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7582
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7580
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7579
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7577
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7576
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7575
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7574
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7574 - val_accuracy: 0.3680 - val_loss: 1.7448
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8106
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3744 - loss: 1.6898  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3750 - loss: 1.7022
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7154
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7245
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7340
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7383
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7416
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7441
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7462
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7481
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7492
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7494
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7495
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7495
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7492
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7487
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7484
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3609 - loss: 1.7482
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3612 - loss: 1.7481
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7480
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3617 - loss: 1.7478
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7477
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7475
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7473
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7472
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7471
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7468
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7466
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7464
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3639 - loss: 1.7462
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7459
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7457
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7454
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7451
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7448
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7444
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7440
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7435
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7431
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7427
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7423
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7420
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7416
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7413
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7412 - val_accuracy: 0.3576 - val_loss: 1.7661
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.6250 - loss: 1.1759
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4149 - loss: 1.6244  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3993 - loss: 1.6507
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3940 - loss: 1.6682
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3922 - loss: 1.6716
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3914 - loss: 1.6762
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3904 - loss: 1.6788
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3903 - loss: 1.6813
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3902 - loss: 1.6831
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3902 - loss: 1.6843
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3905 - loss: 1.6846
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3902 - loss: 1.6858
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3900 - loss: 1.6866
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3897 - loss: 1.6872
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3893 - loss: 1.6879
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3890 - loss: 1.6886
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3886 - loss: 1.6896
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3882 - loss: 1.6907
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3878 - loss: 1.6919
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3875 - loss: 1.6928
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3872 - loss: 1.6939
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6950
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6959
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3863 - loss: 1.6967
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3859 - loss: 1.6976
[1m 651/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3855 - loss: 1.6984
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3852 - loss: 1.6991
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3848 - loss: 1.6998
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3845 - loss: 1.7003
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3841 - loss: 1.7009
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3839 - loss: 1.7013
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3836 - loss: 1.7017
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3834 - loss: 1.7021
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3831 - loss: 1.7026
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3829 - loss: 1.7031
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3827 - loss: 1.7036
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3825 - loss: 1.7040
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3824 - loss: 1.7044
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3823 - loss: 1.7047
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3822 - loss: 1.7049
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3821 - loss: 1.7052
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3820 - loss: 1.7055
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3819 - loss: 1.7057
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3818 - loss: 1.7060
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3817 - loss: 1.7062
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3817 - loss: 1.7064 - val_accuracy: 0.3665 - val_loss: 1.7743
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.3129
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4351 - loss: 1.5869  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4169 - loss: 1.6183
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4069 - loss: 1.6320
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6405
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3954 - loss: 1.6512
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3912 - loss: 1.6581
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3886 - loss: 1.6631
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3873 - loss: 1.6667
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3862 - loss: 1.6694
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3857 - loss: 1.6713
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3855 - loss: 1.6723
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3854 - loss: 1.6732
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3855 - loss: 1.6741
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3855 - loss: 1.6751
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3852 - loss: 1.6763
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3849 - loss: 1.6773
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3847 - loss: 1.6783
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6789
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3846 - loss: 1.6794
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6795
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3845 - loss: 1.6796
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3844 - loss: 1.6796
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3844 - loss: 1.6797
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6797
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6797
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6796
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6796
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6795
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3841 - loss: 1.6796
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3841 - loss: 1.6796
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3840 - loss: 1.6797
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3839 - loss: 1.6798
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3838 - loss: 1.6800
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3838 - loss: 1.6803
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3837 - loss: 1.6805
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3836 - loss: 1.6808
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3836 - loss: 1.6810
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3836 - loss: 1.6812
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3836 - loss: 1.6814
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3836 - loss: 1.6817
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6819
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6822
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6824
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6827
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3834 - loss: 1.6828 - val_accuracy: 0.3402 - val_loss: 1.7893
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.5026
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4187 - loss: 1.6503  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4128 - loss: 1.6491
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4079 - loss: 1.6486
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4037 - loss: 1.6510
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4022 - loss: 1.6519
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4001 - loss: 1.6546
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3989 - loss: 1.6560
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3975 - loss: 1.6577
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6595
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6611
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3945 - loss: 1.6624
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3939 - loss: 1.6635
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6646
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3932 - loss: 1.6655
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6663
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3929 - loss: 1.6671
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6675
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3926 - loss: 1.6678
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6680
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6682
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3929 - loss: 1.6683
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6685
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3931 - loss: 1.6688
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3931 - loss: 1.6693
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3932 - loss: 1.6697
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3933 - loss: 1.6700
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3933 - loss: 1.6702
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3933 - loss: 1.6704
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3933 - loss: 1.6706
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6707
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6709
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6711
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6713
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6715
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6716
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6717
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6718
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6719
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6720
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6720
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6720
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6721
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6721
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6722 - val_accuracy: 0.3706 - val_loss: 1.7485
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8267
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4044 - loss: 1.6673  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4070 - loss: 1.6594
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4072 - loss: 1.6592
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4074 - loss: 1.6580
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4076 - loss: 1.6556
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4087 - loss: 1.6531
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4099 - loss: 1.6497
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4109 - loss: 1.6476
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4120 - loss: 1.6451
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4125 - loss: 1.6435
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4127 - loss: 1.6423
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4129 - loss: 1.6412
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4128 - loss: 1.6406
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4127 - loss: 1.6403
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4125 - loss: 1.6407
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4123 - loss: 1.6410
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4121 - loss: 1.6414
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4118 - loss: 1.6417
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4116 - loss: 1.6419
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4113 - loss: 1.6421
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4110 - loss: 1.6423
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4107 - loss: 1.6427
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4104 - loss: 1.6430
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4100 - loss: 1.6434
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4097 - loss: 1.6438
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4095 - loss: 1.6441
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4092 - loss: 1.6444
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4089 - loss: 1.6447
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4086 - loss: 1.6450
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4083 - loss: 1.6451
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4080 - loss: 1.6452
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4077 - loss: 1.6453
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4074 - loss: 1.6454
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4072 - loss: 1.6455
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4070 - loss: 1.6457
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4068 - loss: 1.6458
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4065 - loss: 1.6461
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4063 - loss: 1.6463
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.4061 - loss: 1.6465
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4059 - loss: 1.6467
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.4057 - loss: 1.6469
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4055 - loss: 1.6471
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4053 - loss: 1.6473
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.4051 - loss: 1.6474
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.4051 - loss: 1.6474 - val_accuracy: 0.3526 - val_loss: 1.7782

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:30[0m 1s/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 955us/step2025-10-31 15:50:45.969163: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:27[0m 1s/step
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m107/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 953us/step
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 914us/step
[1m219/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 926us/step
[1m277/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 913us/step
[1m330/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 919us/step
[1m387/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 913us/step
[1m442/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 915us/step
[1m497/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 915us/step
[1m553/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 913us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 986us/step
[1m107/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 950us/step
[1m166/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 917us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 38.52 [%]
Global F1 score (validation) = 35.32 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.19887902 0.23672342 0.16188237 ... 0.00678116 0.13580431 0.01185271]
 [0.21945469 0.25805765 0.17428364 ... 0.00401418 0.15415592 0.0110636 ]
 [0.23037444 0.21670584 0.1989287  ... 0.00827884 0.18120708 0.05004769]
 ...
 [0.2248483  0.22269037 0.18799768 ... 0.00049982 0.20063101 0.00959215]
 [0.23536283 0.21596918 0.2047096  ... 0.00279291 0.20237821 0.03312962]
 [0.22414051 0.2583659  0.18452372 ... 0.00390736 0.1601822  0.01770293]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 45.48 [%]
Global accuracy score (test) = 33.36 [%]
Global F1 score (train) = 42.34 [%]
Global F1 score (test) = 30.93 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.18      0.21      0.19       184
 CAMINAR CON MÓVIL O LIBRO       0.21      0.56      0.31       184
       CAMINAR USUAL SPEED       0.00      0.00      0.00       184
            CAMINAR ZIGZAG       0.61      0.38      0.47       184
          DE PIE BARRIENDO       0.32      0.35      0.34       184
   DE PIE DOBLANDO TOALLAS       0.34      0.18      0.23       184
    DE PIE MOVIENDO LIBROS       0.31      0.41      0.35       184
          DE PIE USANDO PC       0.31      0.59      0.40       184
        FASE REPOSO CON K5       0.97      0.59      0.74       184
INCREMENTAL CICLOERGOMETRO       0.66      0.66      0.66       184
           SENTADO LEYENDO       0.22      0.24      0.23       184
         SENTADO USANDO PC       0.19      0.25      0.22       184
      SENTADO VIENDO LA TV       0.00      0.00      0.00       184
   SUBIR Y BAJAR ESCALERAS       0.15      0.03      0.05       184
                    TROTAR       0.36      0.58      0.45       161

                  accuracy                           0.33      2737
                 macro avg       0.32      0.34      0.31      2737
              weighted avg       0.32      0.33      0.31      2737


Accuracy capturado en la ejecución 22: 33.36 [%]
F1-score capturado en la ejecución 22: 30.93 [%]

=== EJECUCIÓN 23 ===

--- TRAIN (ejecución 23) ---

--- TEST (ejecución 23) ---
2025-10-31 15:50:59.267272: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:50:59.278977: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761922259.292299 1717724 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761922259.296599 1717724 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761922259.306549 1717724 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922259.306580 1717724 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922259.306583 1717724 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922259.306584 1717724 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:50:59.309958: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761922261.690783 1717724 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761922264.854488 1717823 service.cc:152] XLA service 0x7ce5e4004770 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761922264.854528 1717823 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:51:04.919418: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761922265.357534 1717823 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761922267.994471 1717823 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:27[0m 6s/step - accuracy: 0.1250 - loss: 3.2452
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0747 - loss: 3.2978    
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0673 - loss: 3.3449
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0637 - loss: 3.3482
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0634 - loss: 3.3375
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0654 - loss: 3.3225
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0681 - loss: 3.3058
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0703 - loss: 3.2924
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0721 - loss: 3.2797
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0736 - loss: 3.2682
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0748 - loss: 3.2577
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0761 - loss: 3.2462
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0774 - loss: 3.2347
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0786 - loss: 3.2237
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0801 - loss: 3.2116
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0812 - loss: 3.2020
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0824 - loss: 3.1913
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0835 - loss: 3.1811
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0845 - loss: 3.1716
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0855 - loss: 3.1618
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0863 - loss: 3.1531
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0871 - loss: 3.1454
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0880 - loss: 3.1367
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0889 - loss: 3.1279
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0898 - loss: 3.1194
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0905 - loss: 3.1126
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0913 - loss: 3.1049
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0921 - loss: 3.0976
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0928 - loss: 3.0906
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0935 - loss: 3.0837
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0942 - loss: 3.0767
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0949 - loss: 3.0698
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0956 - loss: 3.0632
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0963 - loss: 3.0565
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0970 - loss: 3.0503
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0976 - loss: 3.0444
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0982 - loss: 3.0382
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0988 - loss: 3.0322
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0994 - loss: 3.0265
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0999 - loss: 3.0209
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1004 - loss: 3.0165
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1009 - loss: 3.0113
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1014 - loss: 3.0060
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1019 - loss: 3.0016
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1021 - loss: 2.9991
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1021 - loss: 2.9989 - val_accuracy: 0.1889 - val_loss: 2.2987
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1875 - loss: 2.7689
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1624 - loss: 2.5764  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1517 - loss: 2.5646
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1496 - loss: 2.5489
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1494 - loss: 2.5381
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1495 - loss: 2.5328
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1495 - loss: 2.5296
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1505 - loss: 2.5256
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1518 - loss: 2.5212
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1530 - loss: 2.5173
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1538 - loss: 2.5150
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1542 - loss: 2.5133
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1544 - loss: 2.5118
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1546 - loss: 2.5101
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1548 - loss: 2.5080
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1552 - loss: 2.5062
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1556 - loss: 2.5046
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1560 - loss: 2.5029
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1563 - loss: 2.5013
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1565 - loss: 2.5000
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1567 - loss: 2.4985
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1569 - loss: 2.4969
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1570 - loss: 2.4955
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1572 - loss: 2.4942
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4930
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1575 - loss: 2.4919
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1577 - loss: 2.4908
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1578 - loss: 2.4896
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1578 - loss: 2.4883
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1579 - loss: 2.4873
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1580 - loss: 2.4862
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1580 - loss: 2.4852
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1581 - loss: 2.4841
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1581 - loss: 2.4831
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1582 - loss: 2.4820
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1583 - loss: 2.4809
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1583 - loss: 2.4800
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1584 - loss: 2.4790
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1584 - loss: 2.4780
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1585 - loss: 2.4771
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1585 - loss: 2.4761
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1586 - loss: 2.4751
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1587 - loss: 2.4742
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1587 - loss: 2.4732
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1588 - loss: 2.4723
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1588 - loss: 2.4720 - val_accuracy: 0.1822 - val_loss: 2.2045
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3351
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1524 - loss: 2.3141  
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1587 - loss: 2.3154
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1587 - loss: 2.3276
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1583 - loss: 2.3336
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1579 - loss: 2.3422
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1568 - loss: 2.3498
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1562 - loss: 2.3549
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1557 - loss: 2.3584
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1555 - loss: 2.3605
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1557 - loss: 2.3610
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1558 - loss: 2.3611
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1558 - loss: 2.3614
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1558 - loss: 2.3614
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1560 - loss: 2.3612
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1561 - loss: 2.3610
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1563 - loss: 2.3608
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1565 - loss: 2.3604
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1567 - loss: 2.3597
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1570 - loss: 2.3591
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1574 - loss: 2.3584
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1577 - loss: 2.3576
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1581 - loss: 2.3569
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1584 - loss: 2.3561
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1588 - loss: 2.3554
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1590 - loss: 2.3550
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1593 - loss: 2.3545
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1596 - loss: 2.3541
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1599 - loss: 2.3535
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1601 - loss: 2.3531
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1603 - loss: 2.3526
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1605 - loss: 2.3522
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1607 - loss: 2.3518
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1608 - loss: 2.3513
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1610 - loss: 2.3509
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1612 - loss: 2.3505
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1614 - loss: 2.3501
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1616 - loss: 2.3497
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1618 - loss: 2.3493
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1620 - loss: 2.3490
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1621 - loss: 2.3486
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1623 - loss: 2.3482
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1625 - loss: 2.3477
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1626 - loss: 2.3473
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1628 - loss: 2.3469
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1629 - loss: 2.3467 - val_accuracy: 0.1895 - val_loss: 2.1263
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0000e+00 - loss: 2.4299
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1208 - loss: 2.3320      
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1461 - loss: 2.2874
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1582 - loss: 2.2673
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1638 - loss: 2.2583
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1682 - loss: 2.2536
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1710 - loss: 2.2515
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.2486
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1753 - loss: 2.2459
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1765 - loss: 2.2441
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1776 - loss: 2.2424
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.2413
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1794 - loss: 2.2401
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1803 - loss: 2.2394
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1812 - loss: 2.2392
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1818 - loss: 2.2391
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1823 - loss: 2.2389
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.2384
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1833 - loss: 2.2381
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2379
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1841 - loss: 2.2375
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2373
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1848 - loss: 2.2373
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1850 - loss: 2.2373
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1852 - loss: 2.2376
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2378
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2380
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.2381
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.2383
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.2385
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2386
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1865 - loss: 2.2387
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1866 - loss: 2.2388
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1867 - loss: 2.2390
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1869 - loss: 2.2390
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1870 - loss: 2.2390
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1872 - loss: 2.2390
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1873 - loss: 2.2390
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2390
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1876 - loss: 2.2390
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1877 - loss: 2.2389
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1878 - loss: 2.2389
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.2389
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2389
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2389 - val_accuracy: 0.2163 - val_loss: 2.0716
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8231
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2030 - loss: 2.1814  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1985 - loss: 2.1846
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1995 - loss: 2.1804
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2007 - loss: 2.1805
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2019 - loss: 2.1805
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2031 - loss: 2.1829
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2032 - loss: 2.1863
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2028 - loss: 2.1899
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2024 - loss: 2.1924
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2024 - loss: 2.1943
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2023 - loss: 2.1956
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.1967
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2018 - loss: 2.1975
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2013 - loss: 2.1983
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.1988
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2007 - loss: 2.1993
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2005 - loss: 2.1998
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2002 - loss: 2.2002
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2000 - loss: 2.2005
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1998 - loss: 2.2007
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1997 - loss: 2.2008
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1996 - loss: 2.2010
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1995 - loss: 2.2010
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1994 - loss: 2.2009
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1994 - loss: 2.2008
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1994 - loss: 2.2007
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1994 - loss: 2.2005
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1993 - loss: 2.2003
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1993 - loss: 2.2001
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1993 - loss: 2.1999
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1992 - loss: 2.1997
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1992 - loss: 2.1995
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1992 - loss: 2.1993
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1993 - loss: 2.1990
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1993 - loss: 2.1987
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1994 - loss: 2.1985
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1994 - loss: 2.1982
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1995 - loss: 2.1980
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1996 - loss: 2.1978
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1996 - loss: 2.1976
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1997 - loss: 2.1974
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1998 - loss: 2.1972
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1998 - loss: 2.1970
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.1999 - loss: 2.1968
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1999 - loss: 2.1968 - val_accuracy: 0.2229 - val_loss: 2.0262
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.5312
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1923 - loss: 2.3191  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2058 - loss: 2.2688
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2121 - loss: 2.2430
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2149 - loss: 2.2271
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2166 - loss: 2.2141
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2174 - loss: 2.2056
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2180 - loss: 2.1993
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2183 - loss: 2.1940
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1893
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1856
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1824
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.1797
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2183 - loss: 2.1772
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2181 - loss: 2.1749
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2180 - loss: 2.1728
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2181 - loss: 2.1712
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2182 - loss: 2.1695
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2184 - loss: 2.1679
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2187 - loss: 2.1661
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2191 - loss: 2.1643
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2194 - loss: 2.1629
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2198 - loss: 2.1615
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2200 - loss: 2.1603
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2203 - loss: 2.1593
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2205 - loss: 2.1584
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2207 - loss: 2.1575
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.1568
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2212 - loss: 2.1560
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2215 - loss: 2.1550
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2219 - loss: 2.1541
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2221 - loss: 2.1534
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2224 - loss: 2.1525
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2227 - loss: 2.1516
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2230 - loss: 2.1508
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2233 - loss: 2.1500
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1493
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2237 - loss: 2.1486
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2240 - loss: 2.1478
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2243 - loss: 2.1470
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.1462
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2248 - loss: 2.1454
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2250 - loss: 2.1447
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2253 - loss: 2.1440
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2253 - loss: 2.1440 - val_accuracy: 0.2389 - val_loss: 2.0377
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.8894
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2310 - loss: 2.1062  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2296 - loss: 2.1035
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2280 - loss: 2.1010
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2287 - loss: 2.1069
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2300 - loss: 2.1117
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2322 - loss: 2.1116
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.1110
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2351 - loss: 2.1098
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.1081
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2368 - loss: 2.1068
[1m 302/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.1053
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2385 - loss: 2.1038
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2392 - loss: 2.1024
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2398 - loss: 2.1012
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2403 - loss: 2.1003
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2408 - loss: 2.0995
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2413 - loss: 2.0987
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2418 - loss: 2.0979
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2423 - loss: 2.0969
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.0958
[1m 563/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2433 - loss: 2.0950
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2437 - loss: 2.0942
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2442 - loss: 2.0935
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2447 - loss: 2.0927
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2450 - loss: 2.0920
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2454 - loss: 2.0912
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2458 - loss: 2.0906
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.0898
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2466 - loss: 2.0889
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.0882
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2474 - loss: 2.0875
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2477 - loss: 2.0869
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2481 - loss: 2.0862
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2484 - loss: 2.0855
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2488 - loss: 2.0847
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2490 - loss: 2.0840
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2493 - loss: 2.0834
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2496 - loss: 2.0828
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2499 - loss: 2.0821
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2502 - loss: 2.0815
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0808
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2507 - loss: 2.0803
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.0798
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2510 - loss: 2.0794 - val_accuracy: 0.2992 - val_loss: 1.9227
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.5000 - loss: 1.7190
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2731 - loss: 1.9788  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2716 - loss: 1.9942
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2676 - loss: 2.0080
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2642 - loss: 2.0173
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2626 - loss: 2.0218
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2619 - loss: 2.0241
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0243
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2620 - loss: 2.0240
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2627 - loss: 2.0241
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.0246
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0251
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0255
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0253
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.0249
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0248
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 2.0246
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2639 - loss: 2.0243
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2642 - loss: 2.0240
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2646 - loss: 2.0237
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0233
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2655 - loss: 2.0228
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2660 - loss: 2.0221
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2665 - loss: 2.0215
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.0209
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.0203
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2680 - loss: 2.0197
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.0191
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2689 - loss: 2.0185
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2694 - loss: 2.0179
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.0173
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.0167
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0163
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0157
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2714 - loss: 2.0151
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0144
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0138
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.0132
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 2.0127
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2732 - loss: 2.0123
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2734 - loss: 2.0119
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.0116
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2739 - loss: 2.0112
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2742 - loss: 2.0109
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2744 - loss: 2.0106
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2744 - loss: 2.0106 - val_accuracy: 0.3129 - val_loss: 1.8640
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7676
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3109 - loss: 1.9751  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3082 - loss: 1.9584
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9560
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3001 - loss: 1.9626
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2969 - loss: 1.9664
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2949 - loss: 1.9679
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2930 - loss: 1.9701
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2920 - loss: 1.9711
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9724
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9726
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2918 - loss: 1.9723
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2919 - loss: 1.9723
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2921 - loss: 1.9722
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 1.9717
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 1.9712
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2929 - loss: 1.9705
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 1.9698
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 1.9696
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9694
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 1.9693
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 1.9693
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 1.9692
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 1.9692
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 1.9691
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 1.9690
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 1.9687
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 1.9684
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 1.9680
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 1.9677
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9674
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9670
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2948 - loss: 1.9667
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 1.9663
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 1.9661
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 1.9658
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9655
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9653
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9650
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9647
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9644
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9642
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9639
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9637 - val_accuracy: 0.3253 - val_loss: 1.8693
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.3750 - loss: 1.9897
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3225 - loss: 1.9472  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3251 - loss: 1.9370
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3248 - loss: 1.9335
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3228 - loss: 1.9349
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 1.9376
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3181 - loss: 1.9401
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 1.9422
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 1.9434
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 1.9438
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 1.9446
[1m 301/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 1.9456
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 1.9466
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 1.9474
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3091 - loss: 1.9479
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3086 - loss: 1.9487
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 1.9492
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 1.9495
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3073 - loss: 1.9497
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 1.9497
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3069 - loss: 1.9495
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3067 - loss: 1.9493
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3066 - loss: 1.9490
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9488
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.9485
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.9483
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9481
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9477
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9473
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9469
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9465
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 1.9461
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 1.9457
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 1.9454
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 1.9450
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9448
[1m 989/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9445
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 1.9443
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 1.9442
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9440
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9438
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9435
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9431
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9429 - val_accuracy: 0.3426 - val_loss: 1.8003
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.1875 - loss: 1.7731
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3025 - loss: 1.8663  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3046 - loss: 1.8792
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3087 - loss: 1.8853
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 1.8919
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 1.8980
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 1.9016
[1m 193/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 1.9035
[1m 221/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 1.9042
[1m 248/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 1.9041
[1m 273/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3121 - loss: 1.9031
[1m 302/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 1.9012
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.8992
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 1.8973
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 1.8960
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 1.8953
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 1.8946
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 1.8938
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 1.8927
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 1.8918
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3154 - loss: 1.8906
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 1.8898
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3159 - loss: 1.8890
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 1.8884
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3162 - loss: 1.8881
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3164 - loss: 1.8877
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3164 - loss: 1.8873
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8869
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8867
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8865
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3167 - loss: 1.8863
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8861
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8859
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8856
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8854
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8852
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8849
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8847
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 1.8844
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8842
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8839
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8837
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 1.8835
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 1.8833
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8833 - val_accuracy: 0.3299 - val_loss: 1.8339
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.9144
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3255 - loss: 1.8434  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8358
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8304
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8261
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8280
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8294
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8312
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8334
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3404 - loss: 1.8350
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8362
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8371
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8381
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8393
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8401
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8406
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8413
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8420
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8427
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8435
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8440
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8442
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8446
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8449
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8451
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3386 - loss: 1.8454
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8456
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3384 - loss: 1.8457
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8459
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8460
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 1.8462
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8463
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3381 - loss: 1.8464
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8465
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8465
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8465
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3378 - loss: 1.8465
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8465
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8464
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.8464
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.8464
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.8464
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.8465
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8465
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8465
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3374 - loss: 1.8465 - val_accuracy: 0.3796 - val_loss: 1.7844
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2500 - loss: 1.6887
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8515  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3210 - loss: 1.8755
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3206 - loss: 1.8818
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3224 - loss: 1.8814
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 1.8772
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 1.8717
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3279 - loss: 1.8671
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3289 - loss: 1.8634
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3300 - loss: 1.8602
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 1.8585
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8570
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8560
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 1.8556
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3332 - loss: 1.8551
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8543
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8536
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3341 - loss: 1.8530
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8524
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3348 - loss: 1.8518
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8509
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8498
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8487
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8476
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3368 - loss: 1.8466
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8457
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.8448
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3378 - loss: 1.8437
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8428
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8418
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8408
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8399
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8391
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8382
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8374
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8368
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8361
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8355
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8349
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8343
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8338
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8334
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8330
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8327
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8323
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8323 - val_accuracy: 0.3340 - val_loss: 1.8157
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.7515
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7794  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3541 - loss: 1.8067
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3511 - loss: 1.8205
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3503 - loss: 1.8225
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.8220
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.8206
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.8200
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.8199
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3499 - loss: 1.8198
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3498 - loss: 1.8196
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3498 - loss: 1.8193
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3498 - loss: 1.8189
[1m 349/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3499 - loss: 1.8181
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3499 - loss: 1.8174
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3498 - loss: 1.8167
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.8161
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3494 - loss: 1.8157
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3492 - loss: 1.8155
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8151
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8147
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8142
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8139
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8135
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8130
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8126
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.8122
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.8117
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.8112
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.8107
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.8103
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.8100
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3493 - loss: 1.8096
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3493 - loss: 1.8092
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3494 - loss: 1.8089
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3494 - loss: 1.8085
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.8082
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.8079
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3497 - loss: 1.8075
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3498 - loss: 1.8072
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.8069
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.8066
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3500 - loss: 1.8063
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3501 - loss: 1.8061
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3501 - loss: 1.8058 - val_accuracy: 0.3647 - val_loss: 1.7509
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9884
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3271 - loss: 1.8258  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3339 - loss: 1.7930
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3351 - loss: 1.7770
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3368 - loss: 1.7673
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.7622
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3393 - loss: 1.7592
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3406 - loss: 1.7563
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.7545
[1m 246/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 1.7538
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3449 - loss: 1.7531
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.7521
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3480 - loss: 1.7513
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7505
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3506 - loss: 1.7503
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7503
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3521 - loss: 1.7505
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3527 - loss: 1.7507
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7509
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7511
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7515
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7520
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7524
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7527
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7530
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7532
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3556 - loss: 1.7533
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7532
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7533
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7532
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7533
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7533
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7533
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3566 - loss: 1.7533
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7534
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7534
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7533
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7533
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7532
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7532
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7531
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7530
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7530
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7530 - val_accuracy: 0.3669 - val_loss: 1.7917
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.6641
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7457  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3474 - loss: 1.8083
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8097
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3408 - loss: 1.8069
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8007
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3426 - loss: 1.7963
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.7923
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3447 - loss: 1.7891
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3450 - loss: 1.7867
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7849
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7829
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3460 - loss: 1.7816
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3462 - loss: 1.7807
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 1.7801
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.7796
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3467 - loss: 1.7791
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3468 - loss: 1.7788
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3470 - loss: 1.7783
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7778
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.7773
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7768
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3478 - loss: 1.7764
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3481 - loss: 1.7760
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3483 - loss: 1.7756
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3486 - loss: 1.7752
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3489 - loss: 1.7748
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3491 - loss: 1.7743
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7738
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7735
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7732
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7728
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3500 - loss: 1.7724
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7720
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3504 - loss: 1.7717
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3505 - loss: 1.7714
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3507 - loss: 1.7711
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3509 - loss: 1.7708
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7705
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7701
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3513 - loss: 1.7698
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7695
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.7691
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7688
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7685 - val_accuracy: 0.3795 - val_loss: 1.7593
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8225
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3743 - loss: 1.7142  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3811 - loss: 1.7044
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3836 - loss: 1.7035
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3856 - loss: 1.7027
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3865 - loss: 1.7057
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3855 - loss: 1.7084
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3841 - loss: 1.7109
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3829 - loss: 1.7122
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3813 - loss: 1.7132
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3803 - loss: 1.7140
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3796 - loss: 1.7142
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7142
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.7142
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.7147
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3777 - loss: 1.7154
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3776 - loss: 1.7160
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7165
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7167
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3773 - loss: 1.7173
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3773 - loss: 1.7176
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7177
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7178
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3770 - loss: 1.7178
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7178
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3768 - loss: 1.7178
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7178
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3765 - loss: 1.7179
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7180
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3762 - loss: 1.7180
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3760 - loss: 1.7181
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7181
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3758 - loss: 1.7182
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3757 - loss: 1.7182
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3756 - loss: 1.7183
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.7184
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.7185
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7186
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7187
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7187
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3750 - loss: 1.7188
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3750 - loss: 1.7189
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3749 - loss: 1.7189
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3748 - loss: 1.7189
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3748 - loss: 1.7190
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3748 - loss: 1.7190 - val_accuracy: 0.3750 - val_loss: 1.7658
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.9778
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7823  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7663
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7572
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7465
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7386
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7338
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7300
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3672 - loss: 1.7277
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3673 - loss: 1.7263
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7250
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7240
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7225
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7210
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7197
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7186
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3687 - loss: 1.7179
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7172
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7165
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7161
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3700 - loss: 1.7156
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7149
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3706 - loss: 1.7144
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7139
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.7134
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3711 - loss: 1.7131
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7128
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3713 - loss: 1.7127
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7125
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3714 - loss: 1.7124
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7123
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.7121
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7120
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7119
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.7117
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3720 - loss: 1.7116
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3721 - loss: 1.7115
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7114
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7112
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3723 - loss: 1.7111
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3724 - loss: 1.7109
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7108
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7106
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3726 - loss: 1.7104
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3726 - loss: 1.7102 - val_accuracy: 0.3700 - val_loss: 1.7891
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.7611
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3348 - loss: 1.7502  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3508 - loss: 1.7395
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7364
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7327
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7314
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7305
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7281
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7251
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7231
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.7203
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7181
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3739 - loss: 1.7165
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3746 - loss: 1.7151
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3749 - loss: 1.7141
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7132
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7129
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7125
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7122
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7119
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7114
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7108
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7103
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7098
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7093
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7087
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3753 - loss: 1.7083
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7081
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7079
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7076
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7074
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7071
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7068
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7066
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7063
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7060
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7057
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7056
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3751 - loss: 1.7054
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7052
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7050
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7048
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7046
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7045
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3752 - loss: 1.7043 - val_accuracy: 0.3809 - val_loss: 1.7929

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 1s/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:52:06.236275: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:35[0m 1s/step
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m104/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 982us/step
[1m158/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 965us/step
[1m211/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 961us/step
[1m268/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 944us/step
[1m322/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 944us/step
[1m379/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 934us/step
[1m437/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 924us/step
[1m496/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 917us/step
[1m543/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 930us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 50/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m105/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 971us/step
[1m154/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 992us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 35.26 [%]
Global F1 score (validation) = 32.48 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.22848353 0.21262683 0.22428147 ... 0.00235135 0.16414501 0.03073424]
 [0.2363714  0.20880441 0.2535317  ... 0.00167669 0.16599497 0.03339139]
 [0.2065189  0.21043223 0.17877363 ... 0.01418882 0.12138653 0.02248552]
 ...
 [0.1506035  0.19269305 0.11713605 ... 0.00327088 0.07647768 0.00917344]
 [0.20024578 0.18523385 0.21918908 ... 0.0080736  0.19005017 0.07837468]
 [0.21477257 0.23595724 0.1867435  ... 0.0018309  0.10919195 0.01330241]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.71 [%]
Global accuracy score (test) = 35.18 [%]
Global F1 score (train) = 43.3 [%]
Global F1 score (test) = 33.54 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.24      0.22      0.23       184
 CAMINAR CON MÓVIL O LIBRO       0.26      0.30      0.28       184
       CAMINAR USUAL SPEED       0.23      0.32      0.26       184
            CAMINAR ZIGZAG       0.45      0.56      0.50       184
          DE PIE BARRIENDO       0.33      0.41      0.36       184
   DE PIE DOBLANDO TOALLAS       0.42      0.11      0.18       184
    DE PIE MOVIENDO LIBROS       0.33      0.61      0.42       184
          DE PIE USANDO PC       0.27      0.61      0.37       184
        FASE REPOSO CON K5       0.91      0.56      0.69       184
INCREMENTAL CICLOERGOMETRO       0.71      0.52      0.60       184
           SENTADO LEYENDO       0.29      0.36      0.33       184
         SENTADO USANDO PC       0.22      0.15      0.18       184
      SENTADO VIENDO LA TV       0.57      0.12      0.21       184
   SUBIR Y BAJAR ESCALERAS       0.00      0.00      0.00       184
                    TROTAR       0.39      0.45      0.42       161

                  accuracy                           0.35      2737
                 macro avg       0.38      0.35      0.34      2737
              weighted avg       0.38      0.35      0.33      2737


Accuracy capturado en la ejecución 23: 35.18 [%]
F1-score capturado en la ejecución 23: 33.54 [%]

=== EJECUCIÓN 24 ===

--- TRAIN (ejecución 24) ---

--- TEST (ejecución 24) ---
2025-10-31 15:52:19.468380: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:52:19.479627: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761922339.492850 1720957 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761922339.497095 1720957 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761922339.507078 1720957 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922339.507098 1720957 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922339.507100 1720957 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922339.507101 1720957 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:52:19.510310: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761922341.863185 1720957 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761922344.974409 1721067 service.cc:152] XLA service 0x75076c003cb0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761922344.974478 1721067 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:52:25.043232: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761922345.485946 1721067 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761922348.117855 1721067 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46:47[0m 5s/step - accuracy: 0.0625 - loss: 3.5168
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0693 - loss: 3.3747    
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0744 - loss: 3.3340
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0764 - loss: 3.3133
[1m  95/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0761 - loss: 3.2993
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0772 - loss: 3.2827
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0782 - loss: 3.2672
[1m 176/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0787 - loss: 3.2529
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0787 - loss: 3.2422
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0789 - loss: 3.2317
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0793 - loss: 3.2214
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0798 - loss: 3.2099
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0806 - loss: 3.1991
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0817 - loss: 3.1880
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0826 - loss: 3.1782
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0836 - loss: 3.1685
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0845 - loss: 3.1596
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0855 - loss: 3.1506
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0865 - loss: 3.1415
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0874 - loss: 3.1323
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0885 - loss: 3.1228
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0894 - loss: 3.1134
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0903 - loss: 3.1051
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0911 - loss: 3.0968
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0919 - loss: 3.0884
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0925 - loss: 3.0815
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0932 - loss: 3.0740
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0939 - loss: 3.0669
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0945 - loss: 3.0600
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0952 - loss: 3.0537
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0958 - loss: 3.0473
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0965 - loss: 3.0403
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0971 - loss: 3.0340
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0977 - loss: 3.0281
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0983 - loss: 3.0225
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0989 - loss: 3.0169
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0994 - loss: 3.0113
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1000 - loss: 3.0059
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1006 - loss: 3.0003
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1011 - loss: 2.9947
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1016 - loss: 2.9894
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1021 - loss: 2.9847
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1025 - loss: 2.9799
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1030 - loss: 2.9750
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1034 - loss: 2.9704
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1034 - loss: 2.9698
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1034 - loss: 2.9697 - val_accuracy: 0.1643 - val_loss: 2.3017
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2710
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1691 - loss: 2.4734  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1586 - loss: 2.5163
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1545 - loss: 2.5377
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1541 - loss: 2.5397
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1546 - loss: 2.5371
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1551 - loss: 2.5331
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1550 - loss: 2.5285
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1547 - loss: 2.5242
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1546 - loss: 2.5200
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1546 - loss: 2.5166
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1545 - loss: 2.5142
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1543 - loss: 2.5124
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1540 - loss: 2.5109
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1539 - loss: 2.5093
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1537 - loss: 2.5078
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1536 - loss: 2.5065
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.5053
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.5043
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1534 - loss: 2.5032
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.5024
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.5014
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.5004
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.4993
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1536 - loss: 2.4982
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1535 - loss: 2.4972
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1535 - loss: 2.4963
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1535 - loss: 2.4954
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1535 - loss: 2.4943
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1535 - loss: 2.4935
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1535 - loss: 2.4925
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1536 - loss: 2.4916
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1536 - loss: 2.4907
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1536 - loss: 2.4898
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1536 - loss: 2.4889
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1536 - loss: 2.4882
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1536 - loss: 2.4875
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1537 - loss: 2.4867
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1537 - loss: 2.4858
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1538 - loss: 2.4849
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1539 - loss: 2.4840
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1540 - loss: 2.4832
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1540 - loss: 2.4824
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1541 - loss: 2.4814
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1542 - loss: 2.4805
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1542 - loss: 2.4802 - val_accuracy: 0.2168 - val_loss: 2.1895
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.5865
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1112 - loss: 2.4018  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1188 - loss: 2.3739
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1240 - loss: 2.3734
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1278 - loss: 2.3762
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1319 - loss: 2.3750
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1348 - loss: 2.3735
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1376 - loss: 2.3706
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1401 - loss: 2.3684
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1423 - loss: 2.3661
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1448 - loss: 2.3633
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1469 - loss: 2.3611
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1485 - loss: 2.3594
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1499 - loss: 2.3582
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1513 - loss: 2.3570
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1525 - loss: 2.3560
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1536 - loss: 2.3550
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1545 - loss: 2.3542
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1554 - loss: 2.3532
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1561 - loss: 2.3524
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1568 - loss: 2.3516
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1574 - loss: 2.3507
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1580 - loss: 2.3499
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1586 - loss: 2.3491
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1592 - loss: 2.3483
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1597 - loss: 2.3476
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1602 - loss: 2.3469
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1607 - loss: 2.3462
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1611 - loss: 2.3456
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1616 - loss: 2.3448
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1620 - loss: 2.3441
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1623 - loss: 2.3435
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1626 - loss: 2.3429
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1629 - loss: 2.3424
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1632 - loss: 2.3418
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1635 - loss: 2.3412
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1638 - loss: 2.3406
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1641 - loss: 2.3400
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1643 - loss: 2.3395
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1646 - loss: 2.3389
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3384
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3380
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3375
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1653 - loss: 2.3371
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1655 - loss: 2.3367
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1657 - loss: 2.3362
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1658 - loss: 2.3361 - val_accuracy: 0.2033 - val_loss: 2.1271
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9425
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2136 - loss: 2.1689  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2091 - loss: 2.1917
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2051 - loss: 2.2050
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2031 - loss: 2.2145
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.2237
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2007 - loss: 2.2320
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1992 - loss: 2.2386
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1979 - loss: 2.2445
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1967 - loss: 2.2484
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1957 - loss: 2.2516
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1948 - loss: 2.2551
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1941 - loss: 2.2575
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1935 - loss: 2.2597
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1930 - loss: 2.2613
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1925 - loss: 2.2625
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1920 - loss: 2.2635
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1916 - loss: 2.2642
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1912 - loss: 2.2647
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2652
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1905 - loss: 2.2656
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1902 - loss: 2.2659
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1899 - loss: 2.2660
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1896 - loss: 2.2661
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1894 - loss: 2.2662
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1891 - loss: 2.2662
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1889 - loss: 2.2663
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1887 - loss: 2.2663
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1886 - loss: 2.2662
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1884 - loss: 2.2662
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1883 - loss: 2.2662
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1881 - loss: 2.2661
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2660
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.2658
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.2656
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1878 - loss: 2.2654
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1877 - loss: 2.2651
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1877 - loss: 2.2648
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1877 - loss: 2.2645
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1876 - loss: 2.2642
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1876 - loss: 2.2639
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2637
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2633
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1874 - loss: 2.2630
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1874 - loss: 2.2627
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1874 - loss: 2.2626 - val_accuracy: 0.2161 - val_loss: 2.0698
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1401
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2411 - loss: 2.1672  
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2215 - loss: 2.1910
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2150 - loss: 2.1994
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2127 - loss: 2.2027
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2107 - loss: 2.2084
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2089 - loss: 2.2139
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2075 - loss: 2.2174
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2067 - loss: 2.2189
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2063 - loss: 2.2197
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2057 - loss: 2.2201
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2053 - loss: 2.2203
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2050 - loss: 2.2199
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2049 - loss: 2.2194
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2048 - loss: 2.2191
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2046 - loss: 2.2188
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2184
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2044 - loss: 2.2181
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2044 - loss: 2.2178
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2174
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2046 - loss: 2.2170
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2048 - loss: 2.2168
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2050 - loss: 2.2166
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2052 - loss: 2.2164
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2053 - loss: 2.2162
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2055 - loss: 2.2160
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.2157
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2059 - loss: 2.2154
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2060 - loss: 2.2151
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2062 - loss: 2.2147
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.2142
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2065 - loss: 2.2139
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2066 - loss: 2.2136
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2067 - loss: 2.2133
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2068 - loss: 2.2130
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2069 - loss: 2.2127
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2070 - loss: 2.2123
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2072 - loss: 2.2119
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2073 - loss: 2.2115
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2074 - loss: 2.2112
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.2109
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2077 - loss: 2.2105
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2078 - loss: 2.2101
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2079 - loss: 2.2098
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2080 - loss: 2.2095
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2081 - loss: 2.2090
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2081 - loss: 2.2090 - val_accuracy: 0.2494 - val_loss: 2.0216
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7074
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2587 - loss: 2.0370  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2324 - loss: 2.0911
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2246 - loss: 2.1084
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2219 - loss: 2.1156
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2220 - loss: 2.1194
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2227 - loss: 2.1216
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2230 - loss: 2.1238
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2231 - loss: 2.1249
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2237 - loss: 2.1245
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2242 - loss: 2.1241
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2247 - loss: 2.1238
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1235
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2258 - loss: 2.1231
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2263 - loss: 2.1227
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2267 - loss: 2.1225
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2272 - loss: 2.1224
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2276 - loss: 2.1225
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.1226
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2284 - loss: 2.1226
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2288 - loss: 2.1225
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2292 - loss: 2.1225
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.1225
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2299 - loss: 2.1224
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2303 - loss: 2.1224
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2306 - loss: 2.1224
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2310 - loss: 2.1224
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2313 - loss: 2.1225
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2315 - loss: 2.1225
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.1225
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.1225
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2323 - loss: 2.1224
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2325 - loss: 2.1222
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2327 - loss: 2.1221
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2329 - loss: 2.1219
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2331 - loss: 2.1217
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.1215
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.1213
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.1211
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.1210
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.1208
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.1206
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.1204
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2345 - loss: 2.1203
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2346 - loss: 2.1202
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2346 - loss: 2.1201 - val_accuracy: 0.3116 - val_loss: 1.9673
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.8642
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2899 - loss: 2.0068  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2653 - loss: 2.0244
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2593 - loss: 2.0322
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2571 - loss: 2.0409
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2560 - loss: 2.0461
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2552 - loss: 2.0527
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2541 - loss: 2.0568
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.0591
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.0605
[1m 254/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2536 - loss: 2.0616
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2535 - loss: 2.0627
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2532 - loss: 2.0638
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2529 - loss: 2.0648
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2526 - loss: 2.0656
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2524 - loss: 2.0665
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2524 - loss: 2.0673
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2524 - loss: 2.0678
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2525 - loss: 2.0681
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2528 - loss: 2.0683
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2530 - loss: 2.0685
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2532 - loss: 2.0687
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2534 - loss: 2.0688
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2536 - loss: 2.0688
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0687
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.0687
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.0686
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2545 - loss: 2.0684
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.0682
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2549 - loss: 2.0681
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.0681
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2552 - loss: 2.0680
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.0679
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.0677
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.0676
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2557 - loss: 2.0674
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2559 - loss: 2.0672
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.0670
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2563 - loss: 2.0668
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2564 - loss: 2.0666
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2566 - loss: 2.0664
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2568 - loss: 2.0662
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2569 - loss: 2.0660
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2570 - loss: 2.0658
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2572 - loss: 2.0656
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2573 - loss: 2.0654 - val_accuracy: 0.3321 - val_loss: 1.8869
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.7907
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2542 - loss: 2.0082  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2551 - loss: 2.0382
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2568 - loss: 2.0487
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2570 - loss: 2.0507
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2572 - loss: 2.0512
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2580 - loss: 2.0510
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2592 - loss: 2.0499
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2602 - loss: 2.0484
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2613 - loss: 2.0468
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.0447
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2628 - loss: 2.0426
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.0404
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2647 - loss: 2.0383
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2657 - loss: 2.0363
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2665 - loss: 2.0344
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.0327
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.0309
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2684 - loss: 2.0294
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2689 - loss: 2.0283
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.0272
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2697 - loss: 2.0260
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2700 - loss: 2.0250
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.0241
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.0232
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.0224
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.0219
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0214
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.0209
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2712 - loss: 2.0205
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0202
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.0199
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2714 - loss: 2.0197
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2714 - loss: 2.0195
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0193
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2716 - loss: 2.0191
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.0188
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.0185
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0181
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.0178
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2721 - loss: 2.0175
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2721 - loss: 2.0172
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0169
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2723 - loss: 2.0165
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2724 - loss: 2.0162
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2724 - loss: 2.0161 - val_accuracy: 0.3308 - val_loss: 1.8822
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0059
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3104 - loss: 1.9948  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3079 - loss: 1.9749
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3078 - loss: 1.9701
[1m  99/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3065 - loss: 1.9607
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9556
[1m 150/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3014 - loss: 1.9520
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9499
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9472
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9439
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 1.9427
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9424
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 1.9425
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 1.9428
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9430
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 1.9429
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 1.9427
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2976 - loss: 1.9422
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2978 - loss: 1.9420
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2979 - loss: 1.9419
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2979 - loss: 1.9421
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9426
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9433
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9439
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9446
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9451
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 1.9455
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9458
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9462
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9465
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9470
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9473
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9477
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9480
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9484
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9486
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9489
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9492
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9495
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9497
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9500
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9502
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 1.9504
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 1.9506
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9508
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9508 - val_accuracy: 0.3317 - val_loss: 1.8174
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.7931
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3011 - loss: 1.8885  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3010 - loss: 1.8901
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3001 - loss: 1.8931
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3017 - loss: 1.8975
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3024 - loss: 1.8994
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3022 - loss: 1.9042
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 1.9085
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9130
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9166
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 1.9192
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 1.9209
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3033 - loss: 1.9221
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 1.9228
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 1.9234
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 1.9244
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 1.9249
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9254
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9257
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9256
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9256
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9255
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9256
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 1.9257
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 1.9260
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 1.9262
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9265
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9267
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 1.9269
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9272
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9273
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9274
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9276
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9277
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9278
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9279
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9280
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9279
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9279
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9278
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9277
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9276
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 1.9275
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 1.9274
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9274
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9273 - val_accuracy: 0.3528 - val_loss: 1.8053
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 1.6542
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2826 - loss: 1.8863  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2739 - loss: 1.9189
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2758 - loss: 1.9204
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2791 - loss: 1.9166
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2831 - loss: 1.9162
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 1.9162
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2890 - loss: 1.9171
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2908 - loss: 1.9183
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2921 - loss: 1.9194
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 1.9196
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9194
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2957 - loss: 1.9190
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 1.9186
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9180
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 1.9175
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2991 - loss: 1.9173
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 1.9170
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 1.9165
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9160
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 1.9157
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 1.9152
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9147
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 1.9142
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3025 - loss: 1.9136
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 1.9130
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 1.9125
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9122
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9118
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3044 - loss: 1.9113
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 1.9108
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3050 - loss: 1.9104
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9100
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9097
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9094
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 1.9091
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9088
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.9085
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9082
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 1.9080
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3067 - loss: 1.9078
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 1.9075
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 1.9072
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 1.9070
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3072 - loss: 1.9067 - val_accuracy: 0.3634 - val_loss: 1.7896
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5625 - loss: 2.0161
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3752 - loss: 1.8219  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3505 - loss: 1.8537
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3426 - loss: 1.8591
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8600
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3369 - loss: 1.8617
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8630
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3352 - loss: 1.8643
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8659
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8671
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3322 - loss: 1.8681
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8688
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3303 - loss: 1.8693
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 1.8695
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3290 - loss: 1.8699
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 1.8702
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 1.8704
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3277 - loss: 1.8706
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3273 - loss: 1.8707
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3269 - loss: 1.8708
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 1.8707
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 1.8705
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 1.8704
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8703
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3262 - loss: 1.8701
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3261 - loss: 1.8700
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 1.8698
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 1.8696
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 1.8694
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8693
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8692
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8689
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8687
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8686
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 1.8685
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 1.8684
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 1.8683
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 1.8681
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 1.8680
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 1.8678
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 1.8677
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 1.8675
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 1.8674
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 1.8673
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3254 - loss: 1.8671 - val_accuracy: 0.3663 - val_loss: 1.7905
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.5734
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3440 - loss: 1.8130  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3365 - loss: 1.8224
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3343 - loss: 1.8247
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3322 - loss: 1.8246
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8245
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3298 - loss: 1.8251
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3289 - loss: 1.8265
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 1.8274
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3283 - loss: 1.8286
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3279 - loss: 1.8295
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8289
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3286 - loss: 1.8286
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3286 - loss: 1.8286
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3286 - loss: 1.8284
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3286 - loss: 1.8281
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8280
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8281
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8283
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 1.8288
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 1.8294
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3283 - loss: 1.8300
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 1.8307
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3280 - loss: 1.8312
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3280 - loss: 1.8316
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3279 - loss: 1.8319
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3280 - loss: 1.8321
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 1.8323
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 1.8324
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 1.8324
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3281 - loss: 1.8324
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3282 - loss: 1.8323
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3282 - loss: 1.8323
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3283 - loss: 1.8322
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3283 - loss: 1.8322
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8321
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8320
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8320
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8319
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8319
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8319
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8319
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8319
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8319
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3285 - loss: 1.8319
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3285 - loss: 1.8319
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3285 - loss: 1.8320 - val_accuracy: 0.3643 - val_loss: 1.7928
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.5289
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8438  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8507
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8478
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3370 - loss: 1.8471
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8450
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3351 - loss: 1.8436
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3349 - loss: 1.8413
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3349 - loss: 1.8391
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8371
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3341 - loss: 1.8352
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8336
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3334 - loss: 1.8319
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8304
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 1.8291
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 1.8279
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3330 - loss: 1.8270
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8261
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3332 - loss: 1.8254
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3332 - loss: 1.8249
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3334 - loss: 1.8244
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8239
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8233
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8228
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8222
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3349 - loss: 1.8215
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3352 - loss: 1.8210
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3354 - loss: 1.8206
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3356 - loss: 1.8202
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8199
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3358 - loss: 1.8196
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8194
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8193
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8192
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8191
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8190
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8190
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8190
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8190
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8189
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8189
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8188
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8187
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.8187
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8186
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3362 - loss: 1.8186 - val_accuracy: 0.3726 - val_loss: 1.8044
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.1875 - loss: 1.9251
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3056 - loss: 1.8293  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3279 - loss: 1.7703
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3349 - loss: 1.7591
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3396 - loss: 1.7550
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3429 - loss: 1.7525
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3449 - loss: 1.7519
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 1.7530
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.7545
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3483 - loss: 1.7558
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3493 - loss: 1.7565
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.7572
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3507 - loss: 1.7578
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3511 - loss: 1.7583
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7591
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7604
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7616
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7625
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7633
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7640
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7647
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7652
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7657
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7663
[1m 620/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7669
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7675
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.7679
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.7683
[1m 725/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.7687
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7689
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7691
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7694
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7696
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7698
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7700
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7702
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7704
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7706
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7708
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7710
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7711
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7713
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7714
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7715
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7717
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7719
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7719 - val_accuracy: 0.3804 - val_loss: 1.7972
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.3996
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3217 - loss: 1.7489  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3310 - loss: 1.7673
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3364 - loss: 1.7698
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3401 - loss: 1.7707
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3417 - loss: 1.7709
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.7703
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.7719
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3442 - loss: 1.7725
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.7726
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3459 - loss: 1.7723
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3471 - loss: 1.7717
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7714
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3489 - loss: 1.7715
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7714
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3501 - loss: 1.7713
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3506 - loss: 1.7714
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7712
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7710
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7707
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7705
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3528 - loss: 1.7702
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3531 - loss: 1.7702
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3534 - loss: 1.7701
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7701
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7701
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7702
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3540 - loss: 1.7702
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7702
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3543 - loss: 1.7702
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7702
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7703
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7704
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7705
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7705
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7706
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7708
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7709
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7709
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7710
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3551 - loss: 1.7711
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7711
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7712
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3553 - loss: 1.7712
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7712
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3554 - loss: 1.7712 - val_accuracy: 0.3839 - val_loss: 1.7685
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.7660
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3097 - loss: 1.7219  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3270 - loss: 1.7018
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3324 - loss: 1.7071
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3386 - loss: 1.7107
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3416 - loss: 1.7139
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3450 - loss: 1.7155
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3477 - loss: 1.7175
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7202
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3508 - loss: 1.7220
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7229
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7241
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7253
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7263
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7271
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3553 - loss: 1.7278
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7286
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7295
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7306
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7314
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7322
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7329
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7336
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7340
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7346
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7350
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7353
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7357
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7361
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7364
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7367
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7370
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7373
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7375
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7376
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7377
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7379
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7379
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7380
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7380
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7381
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7381
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7381
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7381
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7381
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7381 - val_accuracy: 0.3704 - val_loss: 1.7855
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0890
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.3575 - loss: 1.7978  
[1m  45/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7517
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7392
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7327
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7286
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7243
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3673 - loss: 1.7215
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3677 - loss: 1.7192
[1m 226/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7184
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7183
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3680 - loss: 1.7188
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7189
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7189
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7191
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7191
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7190
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7189
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7186
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7186
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7189
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7191
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7193
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7195
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7197
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7199
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7200
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7200
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3673 - loss: 1.7201
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3672 - loss: 1.7201
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7201
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7201
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7201
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7201
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7202
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7202
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7203
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7204
[1m 973/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7205
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7205
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7206
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7206
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7205
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7205
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7204
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7204
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7204 - val_accuracy: 0.3700 - val_loss: 1.8076
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.5643
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4001 - loss: 1.6214  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3965 - loss: 1.6378
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3919 - loss: 1.6501
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3893 - loss: 1.6619
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6694
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3863 - loss: 1.6740
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3851 - loss: 1.6779
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6811
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3839 - loss: 1.6838
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3835 - loss: 1.6859
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3830 - loss: 1.6880
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3826 - loss: 1.6892
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3820 - loss: 1.6900
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3816 - loss: 1.6903
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3812 - loss: 1.6906
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3808 - loss: 1.6909
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3804 - loss: 1.6913
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3800 - loss: 1.6915
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3796 - loss: 1.6919
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3793 - loss: 1.6920
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3792 - loss: 1.6922
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3790 - loss: 1.6924
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3788 - loss: 1.6928
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.6932
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3783 - loss: 1.6936
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.6940
[1m 703/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3781 - loss: 1.6943
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3779 - loss: 1.6947
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3778 - loss: 1.6950
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6953
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6956
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3776 - loss: 1.6959
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.6961
[1m 892/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6964
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3773 - loss: 1.6965
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3772 - loss: 1.6967
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6968
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3770 - loss: 1.6970
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3769 - loss: 1.6971
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3769 - loss: 1.6972
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3768 - loss: 1.6974
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3768 - loss: 1.6975
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3767 - loss: 1.6977
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6979
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6980 - val_accuracy: 0.3702 - val_loss: 1.7741
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.6282
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4231 - loss: 1.6279  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4168 - loss: 1.6531
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4102 - loss: 1.6696
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4046 - loss: 1.6772
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4014 - loss: 1.6810
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4000 - loss: 1.6801
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3992 - loss: 1.6787
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3980 - loss: 1.6783
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6771
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6760
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6754
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3942 - loss: 1.6750
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3935 - loss: 1.6746
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3929 - loss: 1.6745
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3925 - loss: 1.6745
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3922 - loss: 1.6746
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3918 - loss: 1.6751
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3915 - loss: 1.6754
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3913 - loss: 1.6757
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3911 - loss: 1.6759
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6760
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6760
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3906 - loss: 1.6759
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3903 - loss: 1.6760
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3901 - loss: 1.6763
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3898 - loss: 1.6765
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3897 - loss: 1.6767
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3895 - loss: 1.6769
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3893 - loss: 1.6770
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3891 - loss: 1.6772
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3890 - loss: 1.6772
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3888 - loss: 1.6773
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3887 - loss: 1.6774
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3885 - loss: 1.6776
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3883 - loss: 1.6777
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3882 - loss: 1.6777
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3880 - loss: 1.6778
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6780
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3877 - loss: 1.6781
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3875 - loss: 1.6783
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3873 - loss: 1.6784
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3872 - loss: 1.6787
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6788
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3868 - loss: 1.6790
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6791 - val_accuracy: 0.3586 - val_loss: 1.7953
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.6875 - loss: 1.4107
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4350 - loss: 1.6454  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4201 - loss: 1.6414
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4155 - loss: 1.6397
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4103 - loss: 1.6448
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4070 - loss: 1.6505
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4042 - loss: 1.6533
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4023 - loss: 1.6550
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4011 - loss: 1.6555
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4006 - loss: 1.6558
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4004 - loss: 1.6552
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.4001 - loss: 1.6552
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3998 - loss: 1.6557
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3994 - loss: 1.6562
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3990 - loss: 1.6564
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3988 - loss: 1.6567
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3985 - loss: 1.6569
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3983 - loss: 1.6570
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3982 - loss: 1.6570
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3981 - loss: 1.6570
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3979 - loss: 1.6570
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3978 - loss: 1.6572
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3977 - loss: 1.6574
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3975 - loss: 1.6575
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3974 - loss: 1.6577
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3974 - loss: 1.6578
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3973 - loss: 1.6579
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3972 - loss: 1.6580
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6581
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6581
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6582
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6583
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3965 - loss: 1.6584
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6585
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6586
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6587
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3958 - loss: 1.6588
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3957 - loss: 1.6588
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3956 - loss: 1.6589
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3954 - loss: 1.6589
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6589
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3952 - loss: 1.6589
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6589
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6588
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3950 - loss: 1.6588
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3950 - loss: 1.6588 - val_accuracy: 0.3748 - val_loss: 1.7947

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 1s/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 975us/step2025-10-31 15:53:32.713800: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:11[0m 1s/step
[1m 49/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m104/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 973us/step
[1m158/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 958us/step
[1m216/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 934us/step
[1m275/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 916us/step
[1m332/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 909us/step
[1m391/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 902us/step
[1m450/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 896us/step
[1m509/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 891us/step
[1m565/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 892us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 969us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 55/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 927us/step
[1m112/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 908us/step
[1m168/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 909us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 38.09 [%]
Global F1 score (validation) = 36.68 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.22152704 0.18298759 0.21878551 ... 0.01037313 0.17599192 0.07319479]
 [0.19888659 0.2133583  0.17577414 ... 0.00390232 0.11254229 0.00784551]
 [0.2012082  0.19483075 0.18253061 ... 0.02772787 0.13612768 0.04360213]
 ...
 [0.22785254 0.17430265 0.22233546 ... 0.00088305 0.18429396 0.01698456]
 [0.2367818  0.20542797 0.2284512  ... 0.00230166 0.16077352 0.01406759]
 [0.08594339 0.11688262 0.0783636  ... 0.00936679 0.05251527 0.00401637]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.57 [%]
Global accuracy score (test) = 32.01 [%]
Global F1 score (train) = 44.63 [%]
Global F1 score (test) = 29.89 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.23      0.46      0.30       184
 CAMINAR CON MÓVIL O LIBRO       0.18      0.15      0.16       184
       CAMINAR USUAL SPEED       0.22      0.19      0.20       184
            CAMINAR ZIGZAG       0.50      0.47      0.48       184
          DE PIE BARRIENDO       0.27      0.35      0.30       184
   DE PIE DOBLANDO TOALLAS       0.34      0.24      0.28       184
    DE PIE MOVIENDO LIBROS       0.32      0.41      0.36       184
          DE PIE USANDO PC       0.29      0.51      0.37       184
        FASE REPOSO CON K5       0.63      0.50      0.56       184
INCREMENTAL CICLOERGOMETRO       0.67      0.57      0.61       184
           SENTADO LEYENDO       0.23      0.39      0.29       184
         SENTADO USANDO PC       0.00      0.00      0.00       184
      SENTADO VIENDO LA TV       0.13      0.07      0.09       184
   SUBIR Y BAJAR ESCALERAS       0.00      0.00      0.00       184
                    TROTAR       0.44      0.51      0.47       161

                  accuracy                           0.32      2737
                 macro avg       0.29      0.32      0.30      2737
              weighted avg       0.29      0.32      0.30      2737


Accuracy capturado en la ejecución 24: 32.01 [%]
F1-score capturado en la ejecución 24: 29.89 [%]

=== EJECUCIÓN 25 ===

--- TRAIN (ejecución 25) ---

--- TEST (ejecución 25) ---
2025-10-31 15:53:45.919542: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:53:45.930951: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761922425.944315 1724421 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761922425.948612 1724421 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761922425.958581 1724421 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922425.958602 1724421 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922425.958604 1724421 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922425.958606 1724421 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:53:45.961941: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761922428.315866 1724421 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761922431.387923 1724530 service.cc:152] XLA service 0x7081a801a400 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761922431.387987 1724530 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:53:51.459867: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761922431.877239 1724530 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761922434.505116 1724530 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45:43[0m 5s/step - accuracy: 0.0625 - loss: 3.0353
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.0626 - loss: 3.3332    
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0598 - loss: 3.4081
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0630 - loss: 3.4075
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0636 - loss: 3.4032
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0652 - loss: 3.3933
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0667 - loss: 3.3803
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0680 - loss: 3.3661
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0694 - loss: 3.3514
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0709 - loss: 3.3359
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0721 - loss: 3.3233
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0733 - loss: 3.3097
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0746 - loss: 3.2972
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0759 - loss: 3.2853
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0772 - loss: 3.2728
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0783 - loss: 3.2622
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0794 - loss: 3.2509
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0803 - loss: 3.2413
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0814 - loss: 3.2310
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0823 - loss: 3.2216
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0831 - loss: 3.2126
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0839 - loss: 3.2048
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0847 - loss: 3.1958
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0855 - loss: 3.1877
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0862 - loss: 3.1796
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0869 - loss: 3.1718
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0877 - loss: 3.1636
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0883 - loss: 3.1562
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0889 - loss: 3.1499
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0895 - loss: 3.1429
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0902 - loss: 3.1356
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0907 - loss: 3.1300
[1m 838/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0912 - loss: 3.1237
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0918 - loss: 3.1170
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0923 - loss: 3.1112
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0928 - loss: 3.1047
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0934 - loss: 3.0985
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0938 - loss: 3.0931
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0943 - loss: 3.0870
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0948 - loss: 3.0820
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0952 - loss: 3.0769
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0957 - loss: 3.0717
[1m1095/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0962 - loss: 3.0662
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0967 - loss: 3.0613
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0971 - loss: 3.0563
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.0976 - loss: 3.0517
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.0976 - loss: 3.0515 - val_accuracy: 0.1687 - val_loss: 2.2773
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0671
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1752 - loss: 2.3813  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1553 - loss: 2.4438
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1496 - loss: 2.4675
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1476 - loss: 2.4794
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1459 - loss: 2.4887
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1447 - loss: 2.4959
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1441 - loss: 2.5008
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1436 - loss: 2.5039
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1434 - loss: 2.5055
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1437 - loss: 2.5061
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1441 - loss: 2.5059
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1444 - loss: 2.5057
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1447 - loss: 2.5055
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1450 - loss: 2.5051
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1452 - loss: 2.5047
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1455 - loss: 2.5040
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1457 - loss: 2.5036
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1458 - loss: 2.5031
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1459 - loss: 2.5025
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1459 - loss: 2.5019
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1459 - loss: 2.5013
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1459 - loss: 2.5009
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1458 - loss: 2.5005
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1458 - loss: 2.5000
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1458 - loss: 2.4995
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1458 - loss: 2.4989
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1459 - loss: 2.4981
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.4974
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1461 - loss: 2.4966
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1462 - loss: 2.4958
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1462 - loss: 2.4949
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1463 - loss: 2.4940
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1464 - loss: 2.4932
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1465 - loss: 2.4924
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1465 - loss: 2.4916
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1467 - loss: 2.4907
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1468 - loss: 2.4897
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1469 - loss: 2.4889
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1470 - loss: 2.4880
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1471 - loss: 2.4871
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1473 - loss: 2.4862
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1474 - loss: 2.4853
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1475 - loss: 2.4845
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1476 - loss: 2.4835 - val_accuracy: 0.1896 - val_loss: 2.1602
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4837
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1764 - loss: 2.3786  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1789 - loss: 2.3597
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1763 - loss: 2.3538
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1734 - loss: 2.3526
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1716 - loss: 2.3510
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1706 - loss: 2.3504
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1703 - loss: 2.3502
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1703 - loss: 2.3500
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1703 - loss: 2.3498
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1704 - loss: 2.3495
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1701 - loss: 2.3494
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1700 - loss: 2.3490
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3487
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1697 - loss: 2.3485
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1695 - loss: 2.3484
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1694 - loss: 2.3482
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1693 - loss: 2.3481
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3482
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3480
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1693 - loss: 2.3477
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1695 - loss: 2.3472
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1696 - loss: 2.3467
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1698 - loss: 2.3462
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3457
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1700 - loss: 2.3452
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1702 - loss: 2.3446
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1703 - loss: 2.3441
[1m 730/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1705 - loss: 2.3436
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1706 - loss: 2.3430
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1707 - loss: 2.3426
[1m 810/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3421
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3417
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1710 - loss: 2.3413
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3409
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3405
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3400
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1713 - loss: 2.3395
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3391
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3386
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3381
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1716 - loss: 2.3377
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1717 - loss: 2.3372
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1717 - loss: 2.3367
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3362
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1718 - loss: 2.3358 - val_accuracy: 0.2222 - val_loss: 2.0803
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0000e+00 - loss: 2.3876
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1624 - loss: 2.3143      
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1731 - loss: 2.3073
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1755 - loss: 2.2950
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1772 - loss: 2.2883
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.2849
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1790 - loss: 2.2820
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1801 - loss: 2.2792
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1811 - loss: 2.2769
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1814 - loss: 2.2755
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1818 - loss: 2.2744
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1822 - loss: 2.2737
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1825 - loss: 2.2729
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1827 - loss: 2.2724
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1828 - loss: 2.2719
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1828 - loss: 2.2718
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.2719
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.2720
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1825 - loss: 2.2721
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2721
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2722
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2722
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2720
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1825 - loss: 2.2717
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1825 - loss: 2.2714
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.2710
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1827 - loss: 2.2705
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1827 - loss: 2.2700
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.2695
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1829 - loss: 2.2690
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1830 - loss: 2.2685
[1m 811/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1831 - loss: 2.2679
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1831 - loss: 2.2674
[1m 864/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.2669
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.2665
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1833 - loss: 2.2660
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2656
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2652
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2648
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2643
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2638
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1838 - loss: 2.2633
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2628
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1840 - loss: 2.2624
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1840 - loss: 2.2619
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1841 - loss: 2.2617 - val_accuracy: 0.2080 - val_loss: 2.0406
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3814
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2071 - loss: 2.2472  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1864 - loss: 2.2498
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2458
[1m 112/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1841 - loss: 2.2421
[1m 139/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2397
[1m 167/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2365
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2347
[1m 222/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2322
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1841 - loss: 2.2289
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1844 - loss: 2.2260
[1m 305/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1849 - loss: 2.2232
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2211
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2191
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1860 - loss: 2.2174
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2161
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1867 - loss: 2.2149
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1870 - loss: 2.2141
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1873 - loss: 2.2132
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1876 - loss: 2.2123
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2114
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1884 - loss: 2.2105
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1887 - loss: 2.2098
[1m 630/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1890 - loss: 2.2091
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1894 - loss: 2.2086
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1897 - loss: 2.2079
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1901 - loss: 2.2072
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1905 - loss: 2.2064
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.2057
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1911 - loss: 2.2050
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1914 - loss: 2.2042
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1917 - loss: 2.2034
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1920 - loss: 2.2027
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1923 - loss: 2.2020
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1925 - loss: 2.2013
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1928 - loss: 2.2006
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1930 - loss: 2.2000
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1932 - loss: 2.1994
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1935 - loss: 2.1988
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1937 - loss: 2.1982
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1939 - loss: 2.1977
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1941 - loss: 2.1971
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1943 - loss: 2.1967
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1945 - loss: 2.1962
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1946 - loss: 2.1960 - val_accuracy: 0.2453 - val_loss: 1.9834
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 2.5027
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2182 - loss: 2.1758  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2171 - loss: 2.1529
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2168 - loss: 2.1508
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2159 - loss: 2.1489
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2157 - loss: 2.1486
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2165 - loss: 2.1488
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2171 - loss: 2.1495
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.1489
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2186 - loss: 2.1480
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2194 - loss: 2.1471
[1m 300/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.1465
[1m 325/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2208 - loss: 2.1456
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2215 - loss: 2.1447
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2219 - loss: 2.1440
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2223 - loss: 2.1436
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2225 - loss: 2.1433
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2228 - loss: 2.1430
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2230 - loss: 2.1427
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2233 - loss: 2.1423
[1m 539/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1421
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2237 - loss: 2.1421
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2238 - loss: 2.1422
[1m 615/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2239 - loss: 2.1423
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2240 - loss: 2.1423
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1421
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2241 - loss: 2.1419
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2242 - loss: 2.1418
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2243 - loss: 2.1417
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2244 - loss: 2.1417
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.1416
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.1415
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.1414
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2247 - loss: 2.1412
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2248 - loss: 2.1411
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2249 - loss: 2.1409
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2250 - loss: 2.1408
[1m 982/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2251 - loss: 2.1406
[1m1008/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1404
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2253 - loss: 2.1402
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.1400
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.1397
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2256 - loss: 2.1395
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2258 - loss: 2.1393
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2259 - loss: 2.1390
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2259 - loss: 2.1390 - val_accuracy: 0.2818 - val_loss: 1.9251
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.1757
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2605 - loss: 2.0198  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0518
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2644 - loss: 2.0672
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2638 - loss: 2.0743
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0788
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2625 - loss: 2.0799
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2614 - loss: 2.0814
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.0826
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2601 - loss: 2.0836
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2595 - loss: 2.0837
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2591 - loss: 2.0832
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2588 - loss: 2.0827
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2582 - loss: 2.0827
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2577 - loss: 2.0825
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.0820
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2568 - loss: 2.0816
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.0813
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2559 - loss: 2.0811
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.0811
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2549 - loss: 2.0810
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.0809
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2541 - loss: 2.0806
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0803
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2535 - loss: 2.0801
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.0798
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2530 - loss: 2.0794
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2528 - loss: 2.0791
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2526 - loss: 2.0788
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2526 - loss: 2.0785
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2524 - loss: 2.0783
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2523 - loss: 2.0780
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2523 - loss: 2.0777
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2522 - loss: 2.0775
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2522 - loss: 2.0773
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2522 - loss: 2.0771
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2521 - loss: 2.0770
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2521 - loss: 2.0770
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2520 - loss: 2.0769
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2519 - loss: 2.0769
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2518 - loss: 2.0767
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2518 - loss: 2.0766
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2517 - loss: 2.0765
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0764
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0762
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0762 - val_accuracy: 0.3247 - val_loss: 1.8753
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1642
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2540 - loss: 2.1206  
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2541 - loss: 2.0836
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2560 - loss: 2.0660
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2538 - loss: 2.0605
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2545 - loss: 2.0549
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2560 - loss: 2.0497
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2567 - loss: 2.0471
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.0457
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2582 - loss: 2.0446
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2589 - loss: 2.0437
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2595 - loss: 2.0427
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2602 - loss: 2.0414
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2607 - loss: 2.0400
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2611 - loss: 2.0390
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.0382
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.0374
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2622 - loss: 2.0368
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2625 - loss: 2.0362
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.0355
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.0349
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 2.0342
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.0335
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2643 - loss: 2.0328
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2646 - loss: 2.0320
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2648 - loss: 2.0314
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2651 - loss: 2.0306
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2655 - loss: 2.0299
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2658 - loss: 2.0293
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0287
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2664 - loss: 2.0283
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2666 - loss: 2.0278
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2668 - loss: 2.0274
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2670 - loss: 2.0269
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2672 - loss: 2.0265
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2674 - loss: 2.0261
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2676 - loss: 2.0257
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2678 - loss: 2.0252
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2680 - loss: 2.0248
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2682 - loss: 2.0244
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2684 - loss: 2.0240
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.0236
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2687 - loss: 2.0230
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2689 - loss: 2.0226
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2691 - loss: 2.0223
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2691 - loss: 2.0221 - val_accuracy: 0.3587 - val_loss: 1.8258
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0647
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2485 - loss: 2.0524  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2568 - loss: 2.0587
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2598 - loss: 2.0482
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2650 - loss: 2.0341
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2683 - loss: 2.0218
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.0153
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0098
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2732 - loss: 2.0053
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.0021
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2749 - loss: 1.9997
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 1.9972
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 1.9951
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 1.9937
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2775 - loss: 1.9923
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 1.9911
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2785 - loss: 1.9900
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2789 - loss: 1.9891
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 1.9882
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 1.9875
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 1.9868
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 1.9862
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 1.9856
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 1.9851
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 1.9846
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 1.9840
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 1.9835
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 1.9830
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2810 - loss: 1.9825
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2811 - loss: 1.9821
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2813 - loss: 1.9817
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9814
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2815 - loss: 1.9811
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 1.9807
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 1.9804
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 1.9801
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 1.9799
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2820 - loss: 1.9798
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9795
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 1.9794
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 1.9792
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 1.9790
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 1.9787
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 1.9785
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 1.9783
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2826 - loss: 1.9781 - val_accuracy: 0.3382 - val_loss: 1.8546
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0175
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2779 - loss: 1.8910  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2709 - loss: 1.9139
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2701 - loss: 1.9275
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2710 - loss: 1.9339
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2723 - loss: 1.9387
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2738 - loss: 1.9405
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2755 - loss: 1.9414
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 1.9418
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 1.9419
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 1.9417
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 1.9408
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2836 - loss: 1.9396
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 1.9385
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 1.9377
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2878 - loss: 1.9368
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 1.9360
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2897 - loss: 1.9353
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2904 - loss: 1.9349
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2911 - loss: 1.9347
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9344
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2922 - loss: 1.9342
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 1.9341
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2931 - loss: 1.9340
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2936 - loss: 1.9339
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2939 - loss: 1.9338
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 1.9337
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9335
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 1.9334
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9333
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9331
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 1.9330
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9329
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9328
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2967 - loss: 1.9328
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 1.9327
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9326
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2975 - loss: 1.9325
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9325
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2978 - loss: 1.9323
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9322
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 1.9321
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 1.9320
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 1.9318
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9317
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2988 - loss: 1.9317 - val_accuracy: 0.3626 - val_loss: 1.7741
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.2500 - loss: 2.1594
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2849 - loss: 1.9857  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2898 - loss: 1.9772
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2939 - loss: 1.9605
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9476
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9395
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 1.9341
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9300
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 1.9270
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 1.9249
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 1.9224
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 1.9201
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 1.9189
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 1.9173
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3096 - loss: 1.9161
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 1.9149
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 1.9137
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 1.9126
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 1.9118
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 1.9111
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 1.9105
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 1.9102
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 1.9099
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 1.9096
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 1.9091
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3131 - loss: 1.9086
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3133 - loss: 1.9081
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 1.9077
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3136 - loss: 1.9073
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9069
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3139 - loss: 1.9065
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 1.9062
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 1.9059
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3143 - loss: 1.9055
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3144 - loss: 1.9052
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 1.9049
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3146 - loss: 1.9045
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3146 - loss: 1.9043
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3147 - loss: 1.9040
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3147 - loss: 1.9038
[1m1084/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3147 - loss: 1.9036
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3148 - loss: 1.9035
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3148 - loss: 1.9033
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3148 - loss: 1.9031
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3148 - loss: 1.9031 - val_accuracy: 0.3543 - val_loss: 1.7754
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.8386
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2850 - loss: 1.8734  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3024 - loss: 1.8806
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3086 - loss: 1.8833
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8890
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3137 - loss: 1.8934
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 1.8950
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8942
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3181 - loss: 1.8944
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8945
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8939
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 1.8931
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 1.8921
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 1.8908
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 1.8896
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3230 - loss: 1.8882
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3236 - loss: 1.8869
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8857
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 1.8848
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 1.8840
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3253 - loss: 1.8832
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3256 - loss: 1.8823
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3258 - loss: 1.8818
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3260 - loss: 1.8814
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8809
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 1.8804
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 1.8797
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3271 - loss: 1.8791
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 1.8786
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 1.8780
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 1.8776
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 1.8771
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3281 - loss: 1.8768
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3283 - loss: 1.8764
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3285 - loss: 1.8761
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3286 - loss: 1.8759
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3287 - loss: 1.8757
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8754
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3289 - loss: 1.8752
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3290 - loss: 1.8751
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3290 - loss: 1.8749
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3291 - loss: 1.8748
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3292 - loss: 1.8746
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3293 - loss: 1.8745
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3293 - loss: 1.8744
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3293 - loss: 1.8742 - val_accuracy: 0.3802 - val_loss: 1.7360
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8168
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3573 - loss: 1.8363  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3618 - loss: 1.8350
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3556 - loss: 1.8392
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3513 - loss: 1.8444
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.8464
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3478 - loss: 1.8457
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 1.8443
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3453 - loss: 1.8437
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3448 - loss: 1.8427
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3442 - loss: 1.8421
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 1.8419
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.8414
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3430 - loss: 1.8407
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8400
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8395
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3421 - loss: 1.8394
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8393
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8390
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8389
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8388
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3409 - loss: 1.8388
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8389
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8390
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8392
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8394
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8394
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8393
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8393
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8392
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8392
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8391
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8390
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8388
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8386
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8384
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8382
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8380
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8378
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8376
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8374
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8373
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8371
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8370
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8369
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8368 - val_accuracy: 0.3558 - val_loss: 1.7624
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0940
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3044 - loss: 1.8516  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3095 - loss: 1.8280
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8264
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3139 - loss: 1.8234
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8224
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 1.8200
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 1.8174
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3250 - loss: 1.8157
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3261 - loss: 1.8155
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3271 - loss: 1.8154
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 1.8150
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 1.8144
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 1.8136
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 1.8127
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 1.8123
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8120
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3341 - loss: 1.8120
[1m 467/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8120
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3352 - loss: 1.8121
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3358 - loss: 1.8122
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.8122
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.8123
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3371 - loss: 1.8125
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3375 - loss: 1.8126
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8127
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.8126
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8126
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3386 - loss: 1.8125
[1m 758/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8124
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8123
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8122
[1m 836/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8120
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8118
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8116
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8115
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8112
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8110
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3409 - loss: 1.8109
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8107
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3412 - loss: 1.8106
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8105
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8104
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8103
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8103
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8102 - val_accuracy: 0.3706 - val_loss: 1.7569
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.8195
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3656 - loss: 1.8927  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3652 - loss: 1.8639
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3669 - loss: 1.8417
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3682 - loss: 1.8204
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3678 - loss: 1.8083
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7995
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3672 - loss: 1.7933
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7899
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7872
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7847
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3653 - loss: 1.7829
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7814
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7799
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7786
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7778
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7774
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3637 - loss: 1.7775
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7777
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7779
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7780
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7782
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7785
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7787
[1m 647/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7789
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7790
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7791
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7792
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7793
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7794
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7795
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7796
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7797
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7800
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7802
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7803
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7804
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7805
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7806
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7806
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7807
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7807
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7807
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7807
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7807 - val_accuracy: 0.3706 - val_loss: 1.7670
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9112
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7658  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3476 - loss: 1.7555
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3466 - loss: 1.7547
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7528
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7504
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3521 - loss: 1.7477
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3525 - loss: 1.7464
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3531 - loss: 1.7458
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3537 - loss: 1.7466
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7473
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7479
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7478
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7478
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7481
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7486
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7490
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7490
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7489
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7488
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7487
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7486
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7486
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7486
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7485
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7484
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7484
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7484
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7486
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7487
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7488
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3620 - loss: 1.7489
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3621 - loss: 1.7491
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3623 - loss: 1.7493
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3624 - loss: 1.7494
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7496
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7498
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3627 - loss: 1.7500
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7502
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7504
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7506
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7508
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7510
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7511
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7513
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7513 - val_accuracy: 0.3608 - val_loss: 1.7659
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8344
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4015 - loss: 1.7023  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3993 - loss: 1.7091
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3984 - loss: 1.7114
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3983 - loss: 1.7060
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3972 - loss: 1.7038
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3965 - loss: 1.7027
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3962 - loss: 1.7026
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3961 - loss: 1.7015
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3956 - loss: 1.7008
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3952 - loss: 1.7002
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6992
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3949 - loss: 1.6988
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3946 - loss: 1.6988
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3942 - loss: 1.6989
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3938 - loss: 1.6989
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3933 - loss: 1.6990
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6994
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3921 - loss: 1.6997
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3915 - loss: 1.7002
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3909 - loss: 1.7008
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3902 - loss: 1.7017
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3895 - loss: 1.7026
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3888 - loss: 1.7035
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3882 - loss: 1.7043
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.7051
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3870 - loss: 1.7058
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3864 - loss: 1.7065
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3859 - loss: 1.7073
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3854 - loss: 1.7081
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3849 - loss: 1.7088
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3845 - loss: 1.7094
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3841 - loss: 1.7101
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3837 - loss: 1.7106
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3833 - loss: 1.7111
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3830 - loss: 1.7117
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3826 - loss: 1.7122
[1m 970/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3823 - loss: 1.7127
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3820 - loss: 1.7133
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3817 - loss: 1.7138
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3814 - loss: 1.7143
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3812 - loss: 1.7148
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3809 - loss: 1.7152
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3807 - loss: 1.7156
[1m1160/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3805 - loss: 1.7160
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3804 - loss: 1.7162 - val_accuracy: 0.3641 - val_loss: 1.7833

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 1s/step
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:54:47.666217: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:44[0m 1s/step
[1m 54/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 947us/step
[1m112/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 905us/step
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 910us/step
[1m222/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 910us/step
[1m276/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 918us/step
[1m321/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 946us/step
[1m375/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 943us/step
[1m433/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 933us/step
[1m489/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 932us/step
[1m539/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 939us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 967us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 50/169[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m106/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 964us/step
[1m164/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 930us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 37.48 [%]
Global F1 score (validation) = 34.83 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.16397342 0.15175498 0.20189483 ... 0.00124459 0.18108746 0.03236344]
 [0.20025136 0.2602836  0.19918104 ... 0.00380104 0.15772937 0.01211794]
 [0.1978218  0.2326811  0.2155829  ... 0.0014103  0.20715775 0.04018967]
 ...
 [0.08272488 0.12903924 0.07849862 ... 0.00581607 0.06101595 0.00555688]
 [0.19992042 0.24198596 0.20989242 ... 0.00324994 0.16835456 0.01340695]
 [0.19171883 0.22991483 0.22380774 ... 0.00137011 0.18825072 0.01902827]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.65 [%]
Global accuracy score (test) = 34.02 [%]
Global F1 score (train) = 44.61 [%]
Global F1 score (test) = 32.07 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.00      0.00      0.00       184
 CAMINAR CON MÓVIL O LIBRO       0.22      0.55      0.31       184
       CAMINAR USUAL SPEED       0.13      0.09      0.11       184
            CAMINAR ZIGZAG       0.51      0.47      0.49       184
          DE PIE BARRIENDO       0.29      0.47      0.36       184
   DE PIE DOBLANDO TOALLAS       0.30      0.11      0.16       184
    DE PIE MOVIENDO LIBROS       0.29      0.43      0.35       184
          DE PIE USANDO PC       0.31      0.59      0.41       184
        FASE REPOSO CON K5       0.95      0.53      0.68       184
INCREMENTAL CICLOERGOMETRO       0.71      0.56      0.62       184
           SENTADO LEYENDO       0.26      0.43      0.32       184
         SENTADO USANDO PC       0.39      0.29      0.33       184
      SENTADO VIENDO LA TV       0.35      0.09      0.15       184
   SUBIR Y BAJAR ESCALERAS       0.15      0.06      0.09       184
                    TROTAR       0.43      0.43      0.43       161

                  accuracy                           0.34      2737
                 macro avg       0.35      0.34      0.32      2737
              weighted avg       0.35      0.34      0.32      2737


Accuracy capturado en la ejecución 25: 34.02 [%]
F1-score capturado en la ejecución 25: 32.07 [%]

=== EJECUCIÓN 26 ===

--- TRAIN (ejecución 26) ---

--- TEST (ejecución 26) ---
2025-10-31 15:55:00.891413: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:55:00.902713: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761922500.915801 1727415 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761922500.919978 1727415 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761922500.929871 1727415 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922500.929891 1727415 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922500.929894 1727415 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922500.929896 1727415 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:55:00.932862: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761922503.293778 1727415 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761922506.368203 1727553 service.cc:152] XLA service 0x71b3d801ea90 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761922506.368277 1727553 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:55:06.438427: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761922506.874821 1727553 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761922509.523406 1727553 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46:48[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.4147
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0472 - loss: 3.3574        
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0572 - loss: 3.3386
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0619 - loss: 3.3152
[1m  97/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0660 - loss: 3.2904
[1m 123/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0688 - loss: 3.2722
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0712 - loss: 3.2587
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0732 - loss: 3.2465
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0751 - loss: 3.2347
[1m 231/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0767 - loss: 3.2211
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0780 - loss: 3.2103
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0793 - loss: 3.1986
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0804 - loss: 3.1888
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0816 - loss: 3.1782
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0826 - loss: 3.1696
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0836 - loss: 3.1598
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0845 - loss: 3.1511
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0854 - loss: 3.1423
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0864 - loss: 3.1333
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0874 - loss: 3.1249
[1m 528/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0885 - loss: 3.1160
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0895 - loss: 3.1084
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0903 - loss: 3.1011
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0912 - loss: 3.0937
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0919 - loss: 3.0873
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0927 - loss: 3.0801
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0933 - loss: 3.0738
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0939 - loss: 3.0677
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0946 - loss: 3.0611
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0952 - loss: 3.0546
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0959 - loss: 3.0481
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0965 - loss: 3.0426
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0970 - loss: 3.0368
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0976 - loss: 3.0312
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0982 - loss: 3.0257
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0987 - loss: 3.0203
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0992 - loss: 3.0152
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0997 - loss: 3.0099
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1002 - loss: 3.0047
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1007 - loss: 2.9994
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1012 - loss: 2.9943
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1017 - loss: 2.9898
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1021 - loss: 2.9852
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1026 - loss: 2.9803
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1030 - loss: 2.9759
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1031 - loss: 2.9758 - val_accuracy: 0.1721 - val_loss: 2.3059
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.3406
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1657 - loss: 2.4632  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1551 - loss: 2.4876
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1494 - loss: 2.5029
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1452 - loss: 2.5107
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1432 - loss: 2.5134
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1434 - loss: 2.5132
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1435 - loss: 2.5123
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1439 - loss: 2.5115
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1443 - loss: 2.5112
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1449 - loss: 2.5102
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1454 - loss: 2.5094
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1458 - loss: 2.5088
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1461 - loss: 2.5076
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1465 - loss: 2.5059
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1469 - loss: 2.5044
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1472 - loss: 2.5030
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1475 - loss: 2.5018
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1478 - loss: 2.5005
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1481 - loss: 2.4992
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1483 - loss: 2.4980
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1485 - loss: 2.4967
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1488 - loss: 2.4953
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1492 - loss: 2.4940
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1495 - loss: 2.4926
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1498 - loss: 2.4914
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1501 - loss: 2.4901
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1504 - loss: 2.4889
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1507 - loss: 2.4876
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1509 - loss: 2.4867
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1512 - loss: 2.4855
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1514 - loss: 2.4844
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1516 - loss: 2.4834
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1518 - loss: 2.4825
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1520 - loss: 2.4816
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1521 - loss: 2.4806
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1523 - loss: 2.4797
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1525 - loss: 2.4788
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1526 - loss: 2.4779
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1528 - loss: 2.4771
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1529 - loss: 2.4764
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1530 - loss: 2.4756
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1532 - loss: 2.4748
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1533 - loss: 2.4742
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1533 - loss: 2.4735
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1534 - loss: 2.4731 - val_accuracy: 0.1822 - val_loss: 2.2125
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2854
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1495 - loss: 2.3854  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1470 - loss: 2.3931
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1491 - loss: 2.3907
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1517 - loss: 2.3848
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1547 - loss: 2.3794
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1565 - loss: 2.3762
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1579 - loss: 2.3741
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1590 - loss: 2.3715
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1600 - loss: 2.3691
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1607 - loss: 2.3674
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1616 - loss: 2.3657
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1623 - loss: 2.3647
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1631 - loss: 2.3639
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1638 - loss: 2.3631
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1646 - loss: 2.3623
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3615
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1658 - loss: 2.3607
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1662 - loss: 2.3602
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1667 - loss: 2.3596
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1671 - loss: 2.3589
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1674 - loss: 2.3583
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1676 - loss: 2.3577
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1678 - loss: 2.3572
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1680 - loss: 2.3567
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3563
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1682 - loss: 2.3559
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1684 - loss: 2.3554
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1685 - loss: 2.3549
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1687 - loss: 2.3545
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1688 - loss: 2.3540
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1689 - loss: 2.3535
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1691 - loss: 2.3530
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3525
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1694 - loss: 2.3521
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1694 - loss: 2.3517
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1695 - loss: 2.3513
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1696 - loss: 2.3509
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1697 - loss: 2.3506
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1698 - loss: 2.3502
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1698 - loss: 2.3499
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3496
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1700 - loss: 2.3492
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1700 - loss: 2.3488
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1700 - loss: 2.3484
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1701 - loss: 2.3483 - val_accuracy: 0.1922 - val_loss: 2.1770
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.3125 - loss: 2.4378
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2059 - loss: 2.3555  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1912 - loss: 2.3351
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1891 - loss: 2.3328
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1902 - loss: 2.3256
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1912 - loss: 2.3179
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1912 - loss: 2.3119
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1910 - loss: 2.3078
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1907 - loss: 2.3043
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1901 - loss: 2.3013
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1895 - loss: 2.2990
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1890 - loss: 2.2974
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1886 - loss: 2.2962
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1884 - loss: 2.2952
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1882 - loss: 2.2943
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1881 - loss: 2.2934
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1881 - loss: 2.2923
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2913
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2902
[1m 494/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1879 - loss: 2.2892
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1878 - loss: 2.2881
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1878 - loss: 2.2871
[1m 570/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1877 - loss: 2.2859
[1m 595/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1876 - loss: 2.2850
[1m 619/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2842
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1873 - loss: 2.2834
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1872 - loss: 2.2827
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1872 - loss: 2.2820
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1871 - loss: 2.2812
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1871 - loss: 2.2806
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1871 - loss: 2.2799
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1871 - loss: 2.2792
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1872 - loss: 2.2785
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1872 - loss: 2.2780
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1873 - loss: 2.2775
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1873 - loss: 2.2769
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1873 - loss: 2.2763
[1m 954/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1874 - loss: 2.2758
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.2752
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1876 - loss: 2.2745
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1877 - loss: 2.2739
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1878 - loss: 2.2732
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.2726
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.2720
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2714
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.1881 - loss: 2.2708
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1881 - loss: 2.2708 - val_accuracy: 0.2224 - val_loss: 2.0891
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.1398
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2298 - loss: 2.1368  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2344 - loss: 2.1560
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2288 - loss: 2.1645
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1666
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2226 - loss: 2.1686
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2209 - loss: 2.1715
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2197 - loss: 2.1735
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2184 - loss: 2.1757
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2170 - loss: 2.1782
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2161 - loss: 2.1799
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2152 - loss: 2.1818
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.1835
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2140 - loss: 2.1851
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2134 - loss: 2.1865
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2127 - loss: 2.1876
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2122 - loss: 2.1887
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2117 - loss: 2.1898
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2113 - loss: 2.1907
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2110 - loss: 2.1917
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2107 - loss: 2.1924
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2105 - loss: 2.1930
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2103 - loss: 2.1937
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2102 - loss: 2.1942
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2100 - loss: 2.1948
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2099 - loss: 2.1953
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2098 - loss: 2.1957
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2097 - loss: 2.1961
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2096 - loss: 2.1965
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2094 - loss: 2.1968
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2093 - loss: 2.1972
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2092 - loss: 2.1974
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2091 - loss: 2.1976
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2090 - loss: 2.1978
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2090 - loss: 2.1979
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2089 - loss: 2.1981
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1982
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1982
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1982
[1m1030/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1982
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1981
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1980
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.1979
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2089 - loss: 2.1978
[1m1159/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2089 - loss: 2.1976
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2089 - loss: 2.1976 - val_accuracy: 0.2192 - val_loss: 2.0595
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1375
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2283 - loss: 2.1730  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2380 - loss: 2.1600
[1m  70/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2448 - loss: 2.1501
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2470 - loss: 2.1407
[1m 120/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2463 - loss: 2.1383
[1m 148/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2454 - loss: 2.1363
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2441 - loss: 2.1348
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2426 - loss: 2.1344
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2411 - loss: 2.1346
[1m 253/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2401 - loss: 2.1347
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2393 - loss: 2.1345
[1m 302/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2388 - loss: 2.1341
[1m 328/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.1335
[1m 355/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2376 - loss: 2.1332
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.1332
[1m 404/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2367 - loss: 2.1331
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2363 - loss: 2.1331
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.1329
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2357 - loss: 2.1329
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2354 - loss: 2.1330
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2351 - loss: 2.1330
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2348 - loss: 2.1330
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2347 - loss: 2.1330
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2345 - loss: 2.1331
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2343 - loss: 2.1331
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2341 - loss: 2.1332
[1m 690/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.1332
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.1332
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.1333
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.1334
[1m 795/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.1334
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.1334
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.1334
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.1334
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.1333
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.1333
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.1332
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.1330
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.1328
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.1327
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.1325
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.1324
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.1323
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.1321
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.1319
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2341 - loss: 2.1318 - val_accuracy: 0.3197 - val_loss: 1.9538
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.3125 - loss: 2.1341
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2782 - loss: 2.1298  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1102
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2671 - loss: 2.0965
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2656 - loss: 2.0842
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2640 - loss: 2.0796
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2620 - loss: 2.0789
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.0788
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2605 - loss: 2.0783
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.0778
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2590 - loss: 2.0775
[1m 277/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2583 - loss: 2.0774
[1m 303/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.0780
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2565 - loss: 2.0789
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.0797
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2552 - loss: 2.0805
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.0811
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2541 - loss: 2.0815
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2535 - loss: 2.0820
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2530 - loss: 2.0824
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2526 - loss: 2.0828
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2522 - loss: 2.0831
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2519 - loss: 2.0834
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2517 - loss: 2.0835
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2515 - loss: 2.0835
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2514 - loss: 2.0835
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.0833
[1m 698/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.0830
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.0828
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2510 - loss: 2.0825
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.0821
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.0818
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2510 - loss: 2.0815
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2510 - loss: 2.0811
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.0807
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.0803
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.0799
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.0795
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2513 - loss: 2.0792
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2513 - loss: 2.0789
[1m1034/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2514 - loss: 2.0785
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2515 - loss: 2.0782
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2515 - loss: 2.0778
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0775
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2517 - loss: 2.0772
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2518 - loss: 2.0768
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2518 - loss: 2.0768 - val_accuracy: 0.2890 - val_loss: 1.9707
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.0222
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2690 - loss: 1.9393  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9611
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2856 - loss: 1.9778
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2872 - loss: 1.9899
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2878 - loss: 1.9959
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2871 - loss: 2.0027
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.0077
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.0112
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 2.0153
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 2.0188
[1m 280/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2830 - loss: 2.0217
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2824 - loss: 2.0242
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.0260
[1m 357/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.0276
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 2.0288
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.0297
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.0303
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.0306
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2792 - loss: 2.0308
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 2.0311
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2785 - loss: 2.0314
[1m 568/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 2.0315
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 2.0317
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 2.0317
[1m 646/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2776 - loss: 2.0316
[1m 672/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 2.0316
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 2.0315
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.0315
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.0315
[1m 780/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2768 - loss: 2.0314
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 2.0312
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2766 - loss: 2.0311
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2764 - loss: 2.0311
[1m 887/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2763 - loss: 2.0310
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2761 - loss: 2.0309
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2760 - loss: 2.0308
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2759 - loss: 2.0307
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2758 - loss: 2.0305
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2757 - loss: 2.0303
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2757 - loss: 2.0300
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2756 - loss: 2.0297
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2756 - loss: 2.0294
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2756 - loss: 2.0291
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2755 - loss: 2.0289
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2755 - loss: 2.0288 - val_accuracy: 0.3473 - val_loss: 1.8673
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9978
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2897 - loss: 1.9243  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2852 - loss: 1.9373
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2829 - loss: 1.9546
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2810 - loss: 1.9665
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2803 - loss: 1.9736
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 1.9769
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 1.9793
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 1.9807
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2811 - loss: 1.9809
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 1.9808
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 1.9810
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 1.9811
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 1.9811
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 1.9808
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 1.9807
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9806
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2833 - loss: 1.9804
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2834 - loss: 1.9805
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 1.9805
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 1.9804
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 1.9800
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 1.9796
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 1.9791
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 1.9785
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 1.9780
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 1.9776
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 1.9773
[1m 732/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 1.9770
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 1.9767
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 1.9764
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 1.9762
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 1.9760
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 1.9758
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 1.9756
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 1.9754
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 1.9753
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 1.9752
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 1.9751
[1m1016/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 1.9750
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 1.9748
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 1.9747
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 1.9747
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2861 - loss: 1.9746
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2861 - loss: 1.9745
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2862 - loss: 1.9744 - val_accuracy: 0.3154 - val_loss: 1.8787
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.3750 - loss: 1.8939
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8955  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3142 - loss: 1.8824
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3124 - loss: 1.8875
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3097 - loss: 1.8942
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3069 - loss: 1.9001
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9021
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 1.9032
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 1.9037
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 1.9036
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 1.9031
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 1.9031
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 1.9036
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 1.9038
[1m 368/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9040
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 1.9042
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9044
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 1.9046
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3033 - loss: 1.9050
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 1.9056
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 1.9063
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 1.9069
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3024 - loss: 1.9075
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3023 - loss: 1.9081
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 1.9085
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3019 - loss: 1.9092
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9096
[1m 699/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 1.9100
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3014 - loss: 1.9103
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 1.9106
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 1.9109
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 1.9110
[1m 832/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 1.9112
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 1.9113
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 1.9115
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3014 - loss: 1.9116
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3014 - loss: 1.9118
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 1.9118
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 1.9119
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 1.9120
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9121
[1m1069/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9122
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 1.9123
[1m1122/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3019 - loss: 1.9124
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3019 - loss: 1.9125
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3019 - loss: 1.9125 - val_accuracy: 0.3365 - val_loss: 1.8430
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.8577
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3230 - loss: 1.9625  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3258 - loss: 1.9075
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3275 - loss: 1.8863
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3280 - loss: 1.8774
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 1.8793
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3262 - loss: 1.8813
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3262 - loss: 1.8823
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3256 - loss: 1.8838
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 1.8845
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8851
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 1.8865
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 1.8881
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3233 - loss: 1.8894
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 1.8903
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3227 - loss: 1.8906
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3225 - loss: 1.8909
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3223 - loss: 1.8912
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3220 - loss: 1.8913
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 1.8913
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 1.8914
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3210 - loss: 1.8915
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 1.8916
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 1.8915
[1m 642/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 1.8913
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 1.8913
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 1.8913
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 1.8912
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 1.8912
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 1.8911
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 1.8911
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3192 - loss: 1.8911
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8910
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 1.8909
[1m 905/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8908
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8906
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 1.8904
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8902
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8900
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8898
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8896
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8895
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8893
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 1.8892
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3187 - loss: 1.8891 - val_accuracy: 0.3382 - val_loss: 1.8463
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 1.7078
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3815 - loss: 1.7569  
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7822
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3616 - loss: 1.8011
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3524 - loss: 1.8120
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3461 - loss: 1.8185
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8229
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8249
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3369 - loss: 1.8286
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 1.8313
[1m 251/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8334
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3334 - loss: 1.8360
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3326 - loss: 1.8374
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 1.8385
[1m 359/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3314 - loss: 1.8391
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3308 - loss: 1.8398
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3302 - loss: 1.8407
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8417
[1m 463/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3289 - loss: 1.8427
[1m 486/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3286 - loss: 1.8434
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3283 - loss: 1.8440
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3279 - loss: 1.8444
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3276 - loss: 1.8449
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3273 - loss: 1.8453
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 1.8457
[1m 650/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 1.8461
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3264 - loss: 1.8465
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 1.8469
[1m 726/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8473
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 1.8478
[1m 781/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 1.8482
[1m 806/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3250 - loss: 1.8484
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8488
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 1.8491
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 1.8494
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3243 - loss: 1.8496
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8498
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 1.8501
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 1.8503
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 1.8505
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 1.8507
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 1.8509
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 1.8511
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 1.8514
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 1.8516
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3235 - loss: 1.8518 - val_accuracy: 0.3599 - val_loss: 1.8258
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.3724
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7361  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3487 - loss: 1.7645
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3459 - loss: 1.7767
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3423 - loss: 1.7894
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3395 - loss: 1.7996
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8075
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8110
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3378 - loss: 1.8132
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8140
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8149
[1m 281/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8154
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8151
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8146
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8142
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8137
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8131
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8127
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8124
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8120
[1m 507/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8116
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8113
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8110
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8106
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8102
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8099
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8097
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8096
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8095
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8094
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.8093
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8092
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8091
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8090
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 1.8088
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.8086
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3404 - loss: 1.8084
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8083
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.8082
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3406 - loss: 1.8080
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8079
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8078
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3408 - loss: 1.8077
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3409 - loss: 1.8076
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8076
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8076
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8076 - val_accuracy: 0.3463 - val_loss: 1.8164
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9846
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3297 - loss: 1.7419  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3437 - loss: 1.7388
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3461 - loss: 1.7453
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3458 - loss: 1.7520
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3449 - loss: 1.7574
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3440 - loss: 1.7626
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3438 - loss: 1.7649
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3434 - loss: 1.7677
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3426 - loss: 1.7696
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.7703
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3419 - loss: 1.7707
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3416 - loss: 1.7711
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7719
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.7731
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.7742
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 1.7750
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3400 - loss: 1.7756
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 1.7758
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 1.7762
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.7766
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.7769
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3405 - loss: 1.7771
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3406 - loss: 1.7772
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.7773
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3408 - loss: 1.7775
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3409 - loss: 1.7775
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3411 - loss: 1.7775
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3412 - loss: 1.7774
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3413 - loss: 1.7775
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3415 - loss: 1.7775
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.7776
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.7778
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3420 - loss: 1.7779
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3422 - loss: 1.7781
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3423 - loss: 1.7783
[1m 941/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3424 - loss: 1.7786
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 1.7788
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.7790
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3427 - loss: 1.7791
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.7793
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.7796
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3430 - loss: 1.7797
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3432 - loss: 1.7798
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.7799
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3434 - loss: 1.7800 - val_accuracy: 0.3610 - val_loss: 1.8060
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.4551
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3614 - loss: 1.7177  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7278
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7369
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7446
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7481
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7518
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7548
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3544 - loss: 1.7574
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3540 - loss: 1.7592
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7602
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7611
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7621
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7626
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3531 - loss: 1.7628
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7634
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3528 - loss: 1.7637
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3527 - loss: 1.7639
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7641
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3525 - loss: 1.7642
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7645
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7647
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7650
[1m 610/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7651
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7652
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3522 - loss: 1.7653
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3522 - loss: 1.7654
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3521 - loss: 1.7655
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7656
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7657
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7657
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7657
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7656
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7656
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7654
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7652
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7650
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7648
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3521 - loss: 1.7646
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3522 - loss: 1.7644
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3522 - loss: 1.7642
[1m1089/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3523 - loss: 1.7641
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7639
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7638
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3525 - loss: 1.7637
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3525 - loss: 1.7637 - val_accuracy: 0.3721 - val_loss: 1.7827
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.7356
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7264  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7198
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7221
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7199
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7166
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7153
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7141
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7130
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7112
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7095
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7088
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7084
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7082
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7083
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7090
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7099
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7106
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7113
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7118
[1m 523/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3662 - loss: 1.7121
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7126
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7129
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7133
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7137
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7143
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7148
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7153
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7157
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7160
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7164
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7167
[1m 839/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7170
[1m 866/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7172
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3662 - loss: 1.7175
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3662 - loss: 1.7178
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3662 - loss: 1.7182
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3662 - loss: 1.7185
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7189
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7192
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7196
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7199
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7203
[1m1130/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7206
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7209
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7211 - val_accuracy: 0.3719 - val_loss: 1.8167
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1346
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3209 - loss: 1.8853  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8409
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3431 - loss: 1.8300
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3453 - loss: 1.8237
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3483 - loss: 1.8156
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3507 - loss: 1.8091
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3529 - loss: 1.8039
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3545 - loss: 1.7992
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3559 - loss: 1.7945
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7909
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7869
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7835
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7804
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7773
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7745
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7721
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7696
[1m 472/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7677
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7656
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3641 - loss: 1.7637
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7618
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7600
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7585
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7572
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7559
[1m 685/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7546
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7535
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7524
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7513
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7503
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3661 - loss: 1.7494
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3662 - loss: 1.7485
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7477
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7468
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7459
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7453
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7445
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7439
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7433
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3671 - loss: 1.7427
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3673 - loss: 1.7420
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7414
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7409
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7405
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3677 - loss: 1.7402 - val_accuracy: 0.3648 - val_loss: 1.8216
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.4375 - loss: 1.3940
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3801 - loss: 1.5643  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3694 - loss: 1.6294
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3654 - loss: 1.6573
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3653 - loss: 1.6696
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3660 - loss: 1.6754
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3664 - loss: 1.6786
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3674 - loss: 1.6809
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3681 - loss: 1.6824
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3684 - loss: 1.6837
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3686 - loss: 1.6841
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3688 - loss: 1.6845
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3689 - loss: 1.6847
[1m 350/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.6850
[1m 375/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3692 - loss: 1.6853
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3694 - loss: 1.6856
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3697 - loss: 1.6859
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3700 - loss: 1.6859
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3702 - loss: 1.6858
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3705 - loss: 1.6855
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3707 - loss: 1.6852
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3709 - loss: 1.6853
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.6854
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3711 - loss: 1.6856
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.6857
[1m 669/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3714 - loss: 1.6857
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.6858
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3716 - loss: 1.6860
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3717 - loss: 1.6863
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.6866
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.6869
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3718 - loss: 1.6872
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.6875
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.6879
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.6882
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.6885
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3720 - loss: 1.6888
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3720 - loss: 1.6890
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3720 - loss: 1.6893
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3720 - loss: 1.6896
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.6898
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.6900
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.6902
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3719 - loss: 1.6904
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3719 - loss: 1.6905 - val_accuracy: 0.3935 - val_loss: 1.7849
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.6466
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3113 - loss: 1.8022  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3183 - loss: 1.7588
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3242 - loss: 1.7476
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3284 - loss: 1.7434
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3332 - loss: 1.7372
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.7332
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.7288
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3419 - loss: 1.7265
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3436 - loss: 1.7249
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.7232
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3468 - loss: 1.7211
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7186
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7168
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3513 - loss: 1.7149
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7131
[1m 431/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3538 - loss: 1.7116
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7099
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7084
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3572 - loss: 1.7071
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7057
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7044
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7032
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3611 - loss: 1.7021
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7011
[1m 674/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3625 - loss: 1.7002
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3632 - loss: 1.6993
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3638 - loss: 1.6985
[1m 753/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.6978
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3649 - loss: 1.6972
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3654 - loss: 1.6965
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3659 - loss: 1.6959
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.6954
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3667 - loss: 1.6948
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3670 - loss: 1.6943
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3673 - loss: 1.6939
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3676 - loss: 1.6936
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3680 - loss: 1.6932
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3683 - loss: 1.6928
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3686 - loss: 1.6924
[1m1067/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3688 - loss: 1.6922
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3691 - loss: 1.6919
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.6917
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3695 - loss: 1.6915
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3697 - loss: 1.6913 - val_accuracy: 0.3650 - val_loss: 1.8014
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.7229
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7058  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3783 - loss: 1.6806
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3792 - loss: 1.6749
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3789 - loss: 1.6734
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3787 - loss: 1.6739
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6737
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3800 - loss: 1.6727
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3805 - loss: 1.6711
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3809 - loss: 1.6699
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3812 - loss: 1.6689
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3816 - loss: 1.6683
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3820 - loss: 1.6681
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3821 - loss: 1.6686
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6689
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3825 - loss: 1.6689
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3829 - loss: 1.6688
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3832 - loss: 1.6685
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3836 - loss: 1.6682
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3839 - loss: 1.6680
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3842 - loss: 1.6679
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3844 - loss: 1.6676
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3848 - loss: 1.6672
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3851 - loss: 1.6667
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3855 - loss: 1.6663
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3858 - loss: 1.6658
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3861 - loss: 1.6656
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3863 - loss: 1.6653
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3865 - loss: 1.6652
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3867 - loss: 1.6650
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3869 - loss: 1.6649
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3870 - loss: 1.6648
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3871 - loss: 1.6647
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3872 - loss: 1.6645
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3873 - loss: 1.6644
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3874 - loss: 1.6643
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3875 - loss: 1.6643
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3876 - loss: 1.6642
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3877 - loss: 1.6641
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3878 - loss: 1.6641
[1m1055/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3878 - loss: 1.6640
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6640
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6639
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6639
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6639
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3879 - loss: 1.6639 - val_accuracy: 0.3391 - val_loss: 1.8400

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 1s/step
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 920us/step2025-10-31 15:56:11.421684: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:17[0m 1s/step
[1m 53/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 969us/step
[1m109/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 930us/step
[1m167/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 907us/step
[1m227/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 891us/step
[1m288/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 878us/step
[1m344/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 881us/step
[1m399/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 887us/step
[1m454/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 890us/step
[1m507/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 897us/step
[1m558/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 906us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 937us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 967us/step
[1m107/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 951us/step
[1m161/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 947us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 36.41 [%]
Global F1 score (validation) = 33.24 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.23620492 0.18715577 0.21098958 ... 0.00345984 0.17600529 0.0406888 ]
 [0.2304001  0.22988445 0.18800265 ... 0.0037808  0.12797815 0.01801803]
 [0.2296378  0.21306269 0.18002759 ... 0.00700609 0.13336594 0.01832009]
 ...
 [0.13444473 0.1478492  0.10328808 ... 0.00553375 0.05967525 0.00949788]
 [0.21832298 0.21267064 0.1648265  ... 0.00303936 0.11526036 0.01253493]
 [0.07758415 0.10311062 0.0657149  ... 0.00572833 0.03600035 0.00758856]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 43.89 [%]
Global accuracy score (test) = 29.41 [%]
Global F1 score (train) = 40.34 [%]
Global F1 score (test) = 26.67 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.17      0.40      0.24       184
 CAMINAR CON MÓVIL O LIBRO       0.23      0.13      0.17       184
       CAMINAR USUAL SPEED       0.12      0.07      0.09       184
            CAMINAR ZIGZAG       0.39      0.45      0.42       184
          DE PIE BARRIENDO       0.30      0.36      0.32       184
   DE PIE DOBLANDO TOALLAS       0.21      0.02      0.04       184
    DE PIE MOVIENDO LIBROS       0.28      0.58      0.37       184
          DE PIE USANDO PC       0.32      0.55      0.41       184
        FASE REPOSO CON K5       0.97      0.38      0.54       184
INCREMENTAL CICLOERGOMETRO       0.60      0.44      0.51       184
           SENTADO LEYENDO       0.19      0.26      0.22       184
         SENTADO USANDO PC       0.24      0.37      0.29       184
      SENTADO VIENDO LA TV       0.00      0.00      0.00       184
   SUBIR Y BAJAR ESCALERAS       0.00      0.00      0.00       184
                    TROTAR       0.35      0.42      0.38       161

                  accuracy                           0.29      2737
                 macro avg       0.29      0.30      0.27      2737
              weighted avg       0.29      0.29      0.27      2737


Accuracy capturado en la ejecución 26: 29.41 [%]
F1-score capturado en la ejecución 26: 26.67 [%]

=== EJECUCIÓN 27 ===

--- TRAIN (ejecución 27) ---

--- TEST (ejecución 27) ---
2025-10-31 15:56:24.611538: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:56:24.622881: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761922584.635992 1730776 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761922584.640224 1730776 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761922584.650047 1730776 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922584.650067 1730776 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922584.650069 1730776 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922584.650071 1730776 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:56:24.653335: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761922587.012748 1730776 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761922590.149753 1730910 service.cc:152] XLA service 0x7f02f0019e60 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761922590.149790 1730910 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:56:30.213575: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761922590.631127 1730910 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761922593.263419 1730910 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46:47[0m 5s/step - accuracy: 0.0625 - loss: 3.4977
[1m  22/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0634 - loss: 3.3055    
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0710 - loss: 3.2969
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0724 - loss: 3.2823
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0743 - loss: 3.2701
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0760 - loss: 3.2574
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0777 - loss: 3.2458
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0792 - loss: 3.2342
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0803 - loss: 3.2212
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0813 - loss: 3.2092
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0825 - loss: 3.1975
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0836 - loss: 3.1865
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0846 - loss: 3.1774
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0857 - loss: 3.1668
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0869 - loss: 3.1562
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0878 - loss: 3.1470
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0888 - loss: 3.1380
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0897 - loss: 3.1291
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0907 - loss: 3.1198
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0915 - loss: 3.1116
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0923 - loss: 3.1030
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0931 - loss: 3.0949
[1m 578/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0938 - loss: 3.0872
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0945 - loss: 3.0794
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0951 - loss: 3.0727
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0957 - loss: 3.0657
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0963 - loss: 3.0591
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0969 - loss: 3.0516
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0974 - loss: 3.0450
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0979 - loss: 3.0388
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0984 - loss: 3.0323
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0990 - loss: 3.0260
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0994 - loss: 3.0209
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0999 - loss: 3.0148
[1m 895/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1003 - loss: 3.0096
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1008 - loss: 3.0039
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1013 - loss: 2.9984
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1017 - loss: 2.9934
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1022 - loss: 2.9881
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1026 - loss: 2.9828
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1031 - loss: 2.9778
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1035 - loss: 2.9725
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1039 - loss: 2.9679
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1043 - loss: 2.9631
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1047 - loss: 2.9585
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1047 - loss: 2.9582
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1047 - loss: 2.9580 - val_accuracy: 0.1619 - val_loss: 2.3591
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.0000e+00 - loss: 2.5705
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1185 - loss: 2.5957      
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1199 - loss: 2.5879
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1229 - loss: 2.5712
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1247 - loss: 2.5636
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1264 - loss: 2.5592
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1276 - loss: 2.5561
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1288 - loss: 2.5532
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1297 - loss: 2.5505
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1306 - loss: 2.5479
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1314 - loss: 2.5456
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1322 - loss: 2.5435
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1329 - loss: 2.5417
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1337 - loss: 2.5397
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1345 - loss: 2.5374
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1354 - loss: 2.5350
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1362 - loss: 2.5328
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1369 - loss: 2.5305
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1375 - loss: 2.5283
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1382 - loss: 2.5260
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1389 - loss: 2.5235
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1395 - loss: 2.5215
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1402 - loss: 2.5194
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1408 - loss: 2.5172
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1413 - loss: 2.5152
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1418 - loss: 2.5132
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1422 - loss: 2.5116
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1426 - loss: 2.5099
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1429 - loss: 2.5083
[1m 769/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1433 - loss: 2.5067
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1437 - loss: 2.5051
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1440 - loss: 2.5038
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1443 - loss: 2.5025
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1447 - loss: 2.5012
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1450 - loss: 2.4999
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1453 - loss: 2.4985
[1m 955/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1457 - loss: 2.4972
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1460 - loss: 2.4960
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1463 - loss: 2.4947
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1466 - loss: 2.4934
[1m1062/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1469 - loss: 2.4921
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1472 - loss: 2.4908
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1474 - loss: 2.4895
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1476 - loss: 2.4884
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1478 - loss: 2.4872 - val_accuracy: 0.1741 - val_loss: 2.2072
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.6049
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1654 - loss: 2.3162  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1630 - loss: 2.3137
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3215
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1661 - loss: 2.3305
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1661 - loss: 2.3410
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1662 - loss: 2.3461
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1669 - loss: 2.3474
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1672 - loss: 2.3479
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1676 - loss: 2.3477
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1678 - loss: 2.3470
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1681 - loss: 2.3463
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1685 - loss: 2.3454
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1689 - loss: 2.3447
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1692 - loss: 2.3438
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1695 - loss: 2.3430
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1697 - loss: 2.3424
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1699 - loss: 2.3419
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1701 - loss: 2.3413
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1703 - loss: 2.3407
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1705 - loss: 2.3401
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1706 - loss: 2.3394
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1708 - loss: 2.3388
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1709 - loss: 2.3382
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1710 - loss: 2.3376
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1710 - loss: 2.3371
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3367
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1711 - loss: 2.3363
[1m 742/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3360
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1712 - loss: 2.3357
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1713 - loss: 2.3354
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1713 - loss: 2.3350
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3347
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3343
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1714 - loss: 2.3340
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3335
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3331
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3327
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3324
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3320
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3316
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3313
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3309
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3306
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1715 - loss: 2.3303 - val_accuracy: 0.1885 - val_loss: 2.1567
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.2292
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1345 - loss: 2.2532  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1502 - loss: 2.2880
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1593 - loss: 2.2944
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1646 - loss: 2.2960
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1672 - loss: 2.2977
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1693 - loss: 2.2961
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1701 - loss: 2.2944
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1706 - loss: 2.2936
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.2927
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1715 - loss: 2.2917
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1718 - loss: 2.2913
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1721 - loss: 2.2909
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1725 - loss: 2.2905
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1729 - loss: 2.2899
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1733 - loss: 2.2892
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1736 - loss: 2.2886
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1737 - loss: 2.2880
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1739 - loss: 2.2875
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1740 - loss: 2.2869
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1741 - loss: 2.2864
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1742 - loss: 2.2858
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1743 - loss: 2.2854
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1743 - loss: 2.2849
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1743 - loss: 2.2844
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1743 - loss: 2.2839
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1744 - loss: 2.2834
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1745 - loss: 2.2829
[1m 733/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1746 - loss: 2.2824
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1748 - loss: 2.2818
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1750 - loss: 2.2813
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1751 - loss: 2.2809
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1752 - loss: 2.2805
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1753 - loss: 2.2801
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1755 - loss: 2.2797
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1755 - loss: 2.2793
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1756 - loss: 2.2789
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1758 - loss: 2.2785
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1758 - loss: 2.2780
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1759 - loss: 2.2775
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1761 - loss: 2.2771
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1762 - loss: 2.2767
[1m1106/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1762 - loss: 2.2764
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1763 - loss: 2.2760
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1764 - loss: 2.2756
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1764 - loss: 2.2754 - val_accuracy: 0.1980 - val_loss: 2.0721
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.3692
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2159 - loss: 2.2204  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2163 - loss: 2.2071
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2156 - loss: 2.2013
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2142 - loss: 2.1986
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2139 - loss: 2.1991
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2138 - loss: 2.2003
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2135 - loss: 2.2016
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2128 - loss: 2.2017
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2120 - loss: 2.2014
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2111 - loss: 2.2009
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2102 - loss: 2.2006
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2094 - loss: 2.2006
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2088 - loss: 2.2006
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2084 - loss: 2.2006
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2080 - loss: 2.2005
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2078 - loss: 2.2002
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2076 - loss: 2.1998
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2074 - loss: 2.1995
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2071 - loss: 2.1994
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2069 - loss: 2.1994
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2066 - loss: 2.1996
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2063 - loss: 2.1998
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2061 - loss: 2.2000
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2059 - loss: 2.2000
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.2000
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2055 - loss: 2.2000
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2053 - loss: 2.2000
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2052 - loss: 2.1998
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2050 - loss: 2.1997
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2048 - loss: 2.1997
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2047 - loss: 2.1996
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2046 - loss: 2.1995
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.1994
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.1992
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2043 - loss: 2.1990
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2042 - loss: 2.1987
[1m 976/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2042 - loss: 2.1985
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.1983
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.1981
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.1978
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.1976
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.1974
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.1971
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.1969
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2041 - loss: 2.1969 - val_accuracy: 0.2122 - val_loss: 2.0360
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.5405
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1886 - loss: 2.1606  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1900 - loss: 2.1475
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1921 - loss: 2.1586
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1920 - loss: 2.1690
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1924 - loss: 2.1738
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1931 - loss: 2.1751
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1945 - loss: 2.1760
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1959 - loss: 2.1766
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1972 - loss: 2.1773
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1982 - loss: 2.1774
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1990 - loss: 2.1775
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1997 - loss: 2.1779
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2004 - loss: 2.1786
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2007 - loss: 2.1791
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2009 - loss: 2.1796
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2012 - loss: 2.1800
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2015 - loss: 2.1802
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2018 - loss: 2.1804
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.1803
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2025 - loss: 2.1802
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2029 - loss: 2.1800
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2032 - loss: 2.1797
[1m 606/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2036 - loss: 2.1794
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2039 - loss: 2.1791
[1m 656/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.1788
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.1785
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2047 - loss: 2.1781
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2050 - loss: 2.1778
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2053 - loss: 2.1774
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2056 - loss: 2.1769
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2059 - loss: 2.1765
[1m 844/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2061 - loss: 2.1760
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.1756
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2066 - loss: 2.1752
[1m 921/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2068 - loss: 2.1747
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2070 - loss: 2.1742
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2072 - loss: 2.1738
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2074 - loss: 2.1733
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2077 - loss: 2.1728
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2080 - loss: 2.1722
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.1717
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2085 - loss: 2.1712
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2087 - loss: 2.1707
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2090 - loss: 2.1702
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2091 - loss: 2.1701 - val_accuracy: 0.2424 - val_loss: 2.0282
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9282
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2300 - loss: 2.1281  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2316 - loss: 2.1278
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2363 - loss: 2.1167
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2383 - loss: 2.1135
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2388 - loss: 2.1142
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2390 - loss: 2.1134
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2393 - loss: 2.1119
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2397 - loss: 2.1111
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2400 - loss: 2.1102
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2400 - loss: 2.1094
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2403 - loss: 2.1082
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2404 - loss: 2.1074
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2404 - loss: 2.1069
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2405 - loss: 2.1062
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2405 - loss: 2.1056
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2405 - loss: 2.1052
[1m 436/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.1046
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2408 - loss: 2.1041
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2408 - loss: 2.1037
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2408 - loss: 2.1032
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2408 - loss: 2.1027
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2408 - loss: 2.1023
[1m 590/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2408 - loss: 2.1021
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.1020
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.1019
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2407 - loss: 2.1018
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2406 - loss: 2.1017
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2406 - loss: 2.1016
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2405 - loss: 2.1014
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2406 - loss: 2.1012
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2406 - loss: 2.1010
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2407 - loss: 2.1008
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2408 - loss: 2.1006
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2409 - loss: 2.1003
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2410 - loss: 2.1001
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.0999
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.0998
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2412 - loss: 2.0996
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2412 - loss: 2.0994
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2413 - loss: 2.0992
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2413 - loss: 2.0990
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.0988
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.0985
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2415 - loss: 2.0983
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2415 - loss: 2.0981
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2415 - loss: 2.0981 - val_accuracy: 0.2342 - val_loss: 1.9942
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.9332
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3268 - loss: 1.9782  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3155 - loss: 1.9886
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0004
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0101
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2950 - loss: 2.0154
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2909 - loss: 2.0207
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2873 - loss: 2.0255
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 2.0301
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.0336
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2789 - loss: 2.0365
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2771 - loss: 2.0385
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 2.0396
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2746 - loss: 2.0404
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.0410
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.0415
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2719 - loss: 2.0415
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.0414
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0410
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0408
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2702 - loss: 2.0407
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2698 - loss: 2.0405
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2694 - loss: 2.0405
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2691 - loss: 2.0405
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2687 - loss: 2.0406
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.0408
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2680 - loss: 2.0409
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2678 - loss: 2.0409
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2676 - loss: 2.0409
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2673 - loss: 2.0410
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2671 - loss: 2.0411
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2669 - loss: 2.0412
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2667 - loss: 2.0412
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2665 - loss: 2.0412
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2664 - loss: 2.0412
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2663 - loss: 2.0410
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2662 - loss: 2.0409
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0407
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0405
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0402
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0399
[1m1088/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0396
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0393
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0391
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0388 - val_accuracy: 0.3364 - val_loss: 1.8536
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2212
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2870 - loss: 2.0114  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2791 - loss: 2.0054
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2760 - loss: 2.0018
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2730 - loss: 2.0043
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2714 - loss: 2.0060
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2702 - loss: 2.0089
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2690 - loss: 2.0121
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.0127
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2684 - loss: 2.0129
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.0126
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.0124
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2691 - loss: 2.0121
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2694 - loss: 2.0119
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.0119
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2699 - loss: 2.0118
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2700 - loss: 2.0114
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.0108
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.0101
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2707 - loss: 2.0095
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2709 - loss: 2.0089
[1m 550/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.0083
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2712 - loss: 2.0078
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.0072
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2718 - loss: 2.0066
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.0058
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.0051
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 2.0044
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2733 - loss: 2.0036
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.0029
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0023
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2743 - loss: 2.0017
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2745 - loss: 2.0012
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2748 - loss: 2.0007
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2750 - loss: 2.0002
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2752 - loss: 1.9997
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2755 - loss: 1.9993
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2757 - loss: 1.9989
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2759 - loss: 1.9984
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2762 - loss: 1.9980
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2764 - loss: 1.9974
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 1.9970
[1m1110/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 1.9967
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 1.9963
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2773 - loss: 1.9959
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2774 - loss: 1.9958 - val_accuracy: 0.3332 - val_loss: 1.8395
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8437
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3184 - loss: 1.9869  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9925
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3043 - loss: 1.9804
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3033 - loss: 1.9681
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3019 - loss: 1.9610
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 1.9569
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 1.9539
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9517
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9489
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2983 - loss: 1.9469
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9458
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9453
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 1.9451
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 1.9447
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 1.9441
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 1.9437
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9434
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9428
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9422
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 1.9416
[1m 558/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9413
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 1.9410
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 1.9408
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2957 - loss: 1.9406
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9404
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 1.9402
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9401
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9400
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9400
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9400
[1m 828/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9399
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9398
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9398
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9398
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9397
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9397
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9397
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9397
[1m1033/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9397
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9397
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9397
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9397
[1m1139/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9397
[1m1166/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9397
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2954 - loss: 1.9397 - val_accuracy: 0.3571 - val_loss: 1.7844
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.9052
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3098 - loss: 1.9568  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3030 - loss: 1.9372
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9384
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2966 - loss: 1.9385
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9400
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2996 - loss: 1.9390
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9394
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9394
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3024 - loss: 1.9391
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 1.9374
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9362
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 1.9351
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 1.9337
[1m 362/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 1.9324
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9313
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 1.9306
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3054 - loss: 1.9298
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9291
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 1.9285
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9282
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9279
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9277
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9274
[1m 624/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9273
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9271
[1m 679/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9269
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9269
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9268
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9267
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9266
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9265
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 1.9263
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 1.9260
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 1.9258
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 1.9257
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9255
[1m 967/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9253
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9251
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.9250
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.9248
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.9246
[1m1097/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 1.9244
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.9243
[1m1149/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 1.9241
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3063 - loss: 1.9240 - val_accuracy: 0.3341 - val_loss: 1.8278
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8795
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9441  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3020 - loss: 1.9397
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3061 - loss: 1.9341
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3083 - loss: 1.9260
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 1.9191
[1m 161/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3094 - loss: 1.9146
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 1.9118
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 1.9103
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 1.9097
[1m 259/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 1.9092
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 1.9085
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 1.9068
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 1.9054
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 1.9044
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 1.9037
[1m 421/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 1.9034
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 1.9033
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 1.9029
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 1.9024
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 1.9018
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 1.9011
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 1.9004
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 1.8998
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 1.8992
[1m 665/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3163 - loss: 1.8986
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3165 - loss: 1.8980
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8974
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 1.8967
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8961
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 1.8956
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8952
[1m 846/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8949
[1m 874/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3170 - loss: 1.8945
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8941
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 1.8938
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 1.8934
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8929
[1m1005/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8925
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 1.8922
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8918
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 1.8914
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8911
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3177 - loss: 1.8908
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8904
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3178 - loss: 1.8904 - val_accuracy: 0.3536 - val_loss: 1.7850
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0836
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3462 - loss: 1.8964  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8907
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3345 - loss: 1.8809
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8695
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8650
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 1.8621
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 1.8604
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8595
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8588
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 1.8578
[1m 293/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8569
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8558
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 1.8550
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8545
[1m 395/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8543
[1m 423/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8537
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8531
[1m 476/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8527
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8523
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 1.8517
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8513
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.8510
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3334 - loss: 1.8506
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 1.8502
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8498
[1m 691/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3330 - loss: 1.8496
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3328 - loss: 1.8495
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3326 - loss: 1.8493
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3325 - loss: 1.8491
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3324 - loss: 1.8490
[1m 815/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8489
[1m 842/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3322 - loss: 1.8488
[1m 869/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3321 - loss: 1.8487
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.8487
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3318 - loss: 1.8487
[1m 948/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8486
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8486
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8485
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8483
[1m1052/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8483
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3314 - loss: 1.8482
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3314 - loss: 1.8482
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8482
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8482
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8482 - val_accuracy: 0.3378 - val_loss: 1.8442
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9107
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3373 - loss: 1.8774  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3383 - loss: 1.8551
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3400 - loss: 1.8390
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8242
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3422 - loss: 1.8133
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3421 - loss: 1.8082
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3423 - loss: 1.8059
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3423 - loss: 1.8044
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8031
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3431 - loss: 1.8014
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3436 - loss: 1.7996
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.7987
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3441 - loss: 1.7986
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3441 - loss: 1.7990
[1m 384/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3440 - loss: 1.7997
[1m 410/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 1.8008
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3436 - loss: 1.8019
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3435 - loss: 1.8029
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.8037
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 1.8042
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3430 - loss: 1.8046
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.8050
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.8053
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8056
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8059
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3425 - loss: 1.8062
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3424 - loss: 1.8066
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3422 - loss: 1.8070
[1m 739/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3421 - loss: 1.8073
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3420 - loss: 1.8076
[1m 785/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8079
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8082
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8085
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8089
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8092
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8095
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8098
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8100
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3412 - loss: 1.8103
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3411 - loss: 1.8106
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8109
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3409 - loss: 1.8112
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3409 - loss: 1.8114
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3408 - loss: 1.8116
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3408 - loss: 1.8119
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8121 - val_accuracy: 0.3711 - val_loss: 1.7639
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1875 - loss: 1.6950
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3404 - loss: 1.7970  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7727
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3488 - loss: 1.7692
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3440 - loss: 1.7747
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3415 - loss: 1.7801
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 1.7843
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3420 - loss: 1.7860
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3420 - loss: 1.7869
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.7878
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3425 - loss: 1.7887
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.7891
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.7892
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 1.7890
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3429 - loss: 1.7888
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3431 - loss: 1.7887
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.7888
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3434 - loss: 1.7890
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3434 - loss: 1.7891
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3435 - loss: 1.7891
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3435 - loss: 1.7891
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3436 - loss: 1.7891
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3438 - loss: 1.7890
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.7889
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3440 - loss: 1.7888
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3442 - loss: 1.7886
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3444 - loss: 1.7884
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3445 - loss: 1.7881
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3447 - loss: 1.7880
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3448 - loss: 1.7878
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3449 - loss: 1.7877
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3450 - loss: 1.7876
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7875
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3453 - loss: 1.7874
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.7873
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7873
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3457 - loss: 1.7873
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3457 - loss: 1.7872
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3458 - loss: 1.7872
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3459 - loss: 1.7872
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3459 - loss: 1.7872
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3460 - loss: 1.7872
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3460 - loss: 1.7872
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3461 - loss: 1.7872
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3461 - loss: 1.7872 - val_accuracy: 0.3761 - val_loss: 1.7637
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7066
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3357 - loss: 1.8189  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3404 - loss: 1.8169
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3481 - loss: 1.8078
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3510 - loss: 1.8009
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7952
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3551 - loss: 1.7906
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7874
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7849
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7827
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7809
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3564 - loss: 1.7794
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7787
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7780
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3563 - loss: 1.7775
[1m 400/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7767
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7761
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7755
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7751
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7750
[1m 531/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.7748
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3559 - loss: 1.7748
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3558 - loss: 1.7749
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3556 - loss: 1.7751
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3555 - loss: 1.7752
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3553 - loss: 1.7753
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7753
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3551 - loss: 1.7754
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7754
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7755
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7754
[1m 817/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7753
[1m 841/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7752
[1m 867/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7750
[1m 894/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7748
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3549 - loss: 1.7747
[1m 946/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7745
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7744
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3548 - loss: 1.7742
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7740
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7738
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7735
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.7734
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7732
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7730
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7730 - val_accuracy: 0.3676 - val_loss: 1.7590
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.6050
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7603  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7368
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7271
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3728 - loss: 1.7240
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3729 - loss: 1.7234
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7242
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7250
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3719 - loss: 1.7257
[1m 245/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3712 - loss: 1.7267
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7276
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7285
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7289
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7297
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3696 - loss: 1.7304
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7309
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7313
[1m 460/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7320
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7326
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7329
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3680 - loss: 1.7333
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7336
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7342
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3672 - loss: 1.7346
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7349
[1m 664/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3668 - loss: 1.7352
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7354
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7356
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7358
[1m 767/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7360
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7362
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3662 - loss: 1.7365
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7367
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7370
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3657 - loss: 1.7372
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7375
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3654 - loss: 1.7378
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7380
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7382
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7384
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7385
[1m1085/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7387
[1m1112/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7388
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7390
[1m1165/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7392
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7392 - val_accuracy: 0.3482 - val_loss: 1.8066
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.2500 - loss: 1.5911
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7950  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7741
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7488
[1m  98/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3756 - loss: 1.7414
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3758 - loss: 1.7377
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3754 - loss: 1.7355
[1m 178/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3749 - loss: 1.7343
[1m 201/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3741 - loss: 1.7332
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3731 - loss: 1.7321
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.7311
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7307
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.7309
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3707 - loss: 1.7310
[1m 353/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7309
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7311
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7312
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7317
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3686 - loss: 1.7323
[1m 487/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7328
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7331
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3677 - loss: 1.7333
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7332
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7332
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7330
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7327
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7324
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7322
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7319
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7316
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7313
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7311
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7308
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3676 - loss: 1.7305
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3677 - loss: 1.7301
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7297
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7292
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3680 - loss: 1.7288
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7284
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3681 - loss: 1.7281
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7278
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7274
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7272
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7270
[1m1155/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7267
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3684 - loss: 1.7266 - val_accuracy: 0.3702 - val_loss: 1.7769
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.3727
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3843 - loss: 1.6820  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3873 - loss: 1.6907
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3832 - loss: 1.7005
[1m 111/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3811 - loss: 1.7050
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3802 - loss: 1.7068
[1m 164/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3793 - loss: 1.7077
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3790 - loss: 1.7065
[1m 218/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7048
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7037
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7032
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7024
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3789 - loss: 1.7019
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3789 - loss: 1.7017
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.7017
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3784 - loss: 1.7022
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.7026
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3778 - loss: 1.7026
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3777 - loss: 1.7025
[1m 506/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3776 - loss: 1.7024
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7024
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7024
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7024
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7023
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7021
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3776 - loss: 1.7018
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3776 - loss: 1.7016
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3776 - loss: 1.7014
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7012
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7011
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7010
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7009
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.7009
[1m 885/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7008
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7009
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3773 - loss: 1.7010
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3773 - loss: 1.7011
[1m 993/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7012
[1m1020/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3771 - loss: 1.7013
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3770 - loss: 1.7015
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7017
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7019
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3768 - loss: 1.7021
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7022
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7023 - val_accuracy: 0.3748 - val_loss: 1.7636
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9971
[1m  29/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3254 - loss: 1.7485  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3415 - loss: 1.7178
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7026
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.6978
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3618 - loss: 1.6961
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.6957
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3666 - loss: 1.6956
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3680 - loss: 1.6962
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3694 - loss: 1.6964
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3704 - loss: 1.6971
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.6978
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3715 - loss: 1.6983
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3719 - loss: 1.6990
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3724 - loss: 1.6994
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3727 - loss: 1.6995
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3730 - loss: 1.6992
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3732 - loss: 1.6990
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3734 - loss: 1.6986
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3736 - loss: 1.6982
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3738 - loss: 1.6978
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3740 - loss: 1.6974
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3742 - loss: 1.6971
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3745 - loss: 1.6968
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3747 - loss: 1.6966
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3749 - loss: 1.6964
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3750 - loss: 1.6962
[1m 701/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.6961
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3753 - loss: 1.6961
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3755 - loss: 1.6961
[1m 782/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3756 - loss: 1.6961
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3757 - loss: 1.6961
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3757 - loss: 1.6960
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3758 - loss: 1.6960
[1m 890/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3758 - loss: 1.6958
[1m 916/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3759 - loss: 1.6957
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3759 - loss: 1.6955
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3760 - loss: 1.6953
[1m 997/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3760 - loss: 1.6952
[1m1024/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3761 - loss: 1.6951
[1m1047/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3761 - loss: 1.6951
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3761 - loss: 1.6951
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3761 - loss: 1.6950
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3762 - loss: 1.6949
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3762 - loss: 1.6949
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3762 - loss: 1.6949 - val_accuracy: 0.3710 - val_loss: 1.7792
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8670
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4053 - loss: 1.6788  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3973 - loss: 1.6932
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6971
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3978 - loss: 1.6922
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3983 - loss: 1.6893
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3976 - loss: 1.6891
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6888
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3964 - loss: 1.6892
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3958 - loss: 1.6907
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6916
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3950 - loss: 1.6924
[1m 317/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3947 - loss: 1.6926
[1m 344/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3946 - loss: 1.6923
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3945 - loss: 1.6919
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3943 - loss: 1.6915
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3940 - loss: 1.6910
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3938 - loss: 1.6905
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3937 - loss: 1.6899
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3936 - loss: 1.6892
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6887
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3932 - loss: 1.6882
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6879
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6873
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6867
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6859
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6852
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6844
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6836
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6826
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6818
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6809
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6803
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6796
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3928 - loss: 1.6790
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6784
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6779
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3927 - loss: 1.6773
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3926 - loss: 1.6769
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3926 - loss: 1.6764
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3925 - loss: 1.6760
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3925 - loss: 1.6755
[1m1108/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3924 - loss: 1.6752
[1m1134/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3924 - loss: 1.6749
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3923 - loss: 1.6745
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3923 - loss: 1.6745 - val_accuracy: 0.3765 - val_loss: 1.7973

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:30[0m 1s/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:57:37.494722: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:04[0m 1s/step
[1m 54/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 952us/step
[1m106/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 963us/step
[1m161/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 946us/step
[1m206/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 986us/step
[1m253/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m306/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 996us/step
[1m363/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 980us/step
[1m413/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 982us/step
[1m461/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 990us/step
[1m516/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 982us/step
[1m572/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 974us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 937us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 53/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 977us/step
[1m113/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 906us/step
[1m165/169[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 924us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step
Global accuracy score (validation) = 33.91 [%]
Global F1 score (validation) = 30.86 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.20121115 0.23764907 0.1924516  ... 0.00615674 0.16137686 0.01689503]
 [0.2013896  0.2556759  0.20709133 ... 0.00264694 0.17026624 0.01650281]
 [0.20484684 0.20635009 0.21190822 ... 0.00346026 0.21498963 0.05957331]
 ...
 [0.21316805 0.21928276 0.19724572 ... 0.00343254 0.17597803 0.01446342]
 [0.19605853 0.1584363  0.18676023 ... 0.00104171 0.17584473 0.01918846]
 [0.06015548 0.09196588 0.05727341 ... 0.00883104 0.04000252 0.00605682]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 44.51 [%]
Global accuracy score (test) = 32.96 [%]
Global F1 score (train) = 41.2 [%]
Global F1 score (test) = 30.0 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.16      0.11      0.13       184
 CAMINAR CON MÓVIL O LIBRO       0.21      0.53      0.30       184
       CAMINAR USUAL SPEED       0.14      0.03      0.05       184
            CAMINAR ZIGZAG       0.46      0.49      0.47       184
          DE PIE BARRIENDO       0.36      0.36      0.36       184
   DE PIE DOBLANDO TOALLAS       0.40      0.08      0.13       184
    DE PIE MOVIENDO LIBROS       0.28      0.57      0.38       184
          DE PIE USANDO PC       0.23      0.74      0.35       184
        FASE REPOSO CON K5       0.75      0.61      0.67       184
INCREMENTAL CICLOERGOMETRO       0.83      0.57      0.68       184
           SENTADO LEYENDO       0.44      0.10      0.17       184
         SENTADO USANDO PC       0.26      0.08      0.12       184
      SENTADO VIENDO LA TV       0.30      0.11      0.17       184
   SUBIR Y BAJAR ESCALERAS       0.30      0.07      0.11       184
                    TROTAR       0.37      0.51      0.43       161

                  accuracy                           0.33      2737
                 macro avg       0.37      0.33      0.30      2737
              weighted avg       0.37      0.33      0.30      2737


Accuracy capturado en la ejecución 27: 32.96 [%]
F1-score capturado en la ejecución 27: 30.0 [%]

=== EJECUCIÓN 28 ===

--- TRAIN (ejecución 28) ---

--- TEST (ejecución 28) ---
2025-10-31 15:57:50.797662: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:57:50.809233: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761922670.822467 1734248 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761922670.826650 1734248 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761922670.836363 1734248 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922670.836385 1734248 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922670.836387 1734248 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922670.836388 1734248 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:57:50.839665: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761922673.216128 1734248 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761922676.346169 1734377 service.cc:152] XLA service 0x78b8f801a190 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761922676.346232 1734377 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:57:56.412808: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761922676.832390 1734377 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761922679.516402 1734377 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:38[0m 6s/step - accuracy: 0.0000e+00 - loss: 3.8943
[1m  20/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0449 - loss: 3.6080        
[1m  46/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0495 - loss: 3.6032
[1m  71/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0542 - loss: 3.5627
[1m  94/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0576 - loss: 3.5351
[1m 119/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0606 - loss: 3.5082
[1m 147/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0631 - loss: 3.4820
[1m 173/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0649 - loss: 3.4596
[1m 198/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0668 - loss: 3.4380
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0689 - loss: 3.4155
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0708 - loss: 3.3946
[1m 276/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0725 - loss: 3.3772
[1m 304/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0743 - loss: 3.3585
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0759 - loss: 3.3417
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0774 - loss: 3.3258
[1m 383/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0787 - loss: 3.3120
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0800 - loss: 3.2984
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0812 - loss: 3.2847
[1m 461/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0822 - loss: 3.2736
[1m 488/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0833 - loss: 3.2614
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0843 - loss: 3.2502
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0852 - loss: 3.2395
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0861 - loss: 3.2292
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0869 - loss: 3.2197
[1m 618/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0878 - loss: 3.2097
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0885 - loss: 3.2018
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0893 - loss: 3.1925
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0902 - loss: 3.1832
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0909 - loss: 3.1744
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0916 - loss: 3.1656
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0923 - loss: 3.1576
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0930 - loss: 3.1498
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0937 - loss: 3.1413
[1m 856/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0943 - loss: 3.1343
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0949 - loss: 3.1265
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0956 - loss: 3.1193
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0961 - loss: 3.1128
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0967 - loss: 3.1061
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0972 - loss: 3.1003
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0977 - loss: 3.0942
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0982 - loss: 3.0879
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0988 - loss: 3.0814
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.0993 - loss: 3.0753
[1m1114/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.0998 - loss: 3.0699
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1002 - loss: 3.0642
[1m1167/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1007 - loss: 3.0584
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1008 - loss: 3.0582
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1008 - loss: 3.0579 - val_accuracy: 0.1745 - val_loss: 2.2877
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.3125 - loss: 2.3848
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1985 - loss: 2.5282  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1881 - loss: 2.5046
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1783 - loss: 2.5044
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1722 - loss: 2.5061
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1681 - loss: 2.5068
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1660 - loss: 2.5061
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1645 - loss: 2.5058
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1635 - loss: 2.5058
[1m 230/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1625 - loss: 2.5053
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1615 - loss: 2.5049
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1608 - loss: 2.5038
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1600 - loss: 2.5027
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1594 - loss: 2.5018
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1588 - loss: 2.5010
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1583 - loss: 2.5005
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1578 - loss: 2.5000
[1m 448/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4997
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1570 - loss: 2.4992
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1567 - loss: 2.4988
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1564 - loss: 2.4983
[1m 557/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1562 - loss: 2.4977
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1561 - loss: 2.4970
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1560 - loss: 2.4963
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1560 - loss: 2.4955
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1560 - loss: 2.4948
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1559 - loss: 2.4939
[1m 713/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1559 - loss: 2.4931
[1m 740/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1558 - loss: 2.4923
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1558 - loss: 2.4914
[1m 796/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1558 - loss: 2.4906
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1558 - loss: 2.4898
[1m 851/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1557 - loss: 2.4890
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1557 - loss: 2.4882
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1557 - loss: 2.4874
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1557 - loss: 2.4867
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1556 - loss: 2.4859
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1556 - loss: 2.4851
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4843
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1555 - loss: 2.4835
[1m1063/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4826
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1554 - loss: 2.4818
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1553 - loss: 2.4809
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1553 - loss: 2.4800
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1552 - loss: 2.4791 - val_accuracy: 0.1981 - val_loss: 2.1877
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.0625 - loss: 2.4807
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1612 - loss: 2.3933  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1568 - loss: 2.3980
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1571 - loss: 2.3937
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1577 - loss: 2.3893
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1588 - loss: 2.3852
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1603 - loss: 2.3819
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1611 - loss: 2.3797
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1616 - loss: 2.3784
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1622 - loss: 2.3768
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1630 - loss: 2.3753
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1635 - loss: 2.3738
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1638 - loss: 2.3726
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1642 - loss: 2.3712
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1645 - loss: 2.3698
[1m 390/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1649 - loss: 2.3685
[1m 417/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3671
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1655 - loss: 2.3659
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1657 - loss: 2.3649
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1658 - loss: 2.3638
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1660 - loss: 2.3625
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1662 - loss: 2.3610
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1665 - loss: 2.3596
[1m 603/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1667 - loss: 2.3581
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1669 - loss: 2.3569
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1670 - loss: 2.3558
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1670 - loss: 2.3545
[1m 707/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1671 - loss: 2.3535
[1m 735/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1672 - loss: 2.3525
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1672 - loss: 2.3516
[1m 786/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1672 - loss: 2.3508
[1m 812/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1672 - loss: 2.3500
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1673 - loss: 2.3493
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1673 - loss: 2.3487
[1m 888/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1673 - loss: 2.3480
[1m 915/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1673 - loss: 2.3473
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1673 - loss: 2.3466
[1m 966/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1674 - loss: 2.3460
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1674 - loss: 2.3454
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1675 - loss: 2.3448
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1675 - loss: 2.3442
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1675 - loss: 2.3436
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1676 - loss: 2.3430
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1676 - loss: 2.3423
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1677 - loss: 2.3417
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1678 - loss: 2.3413 - val_accuracy: 0.2130 - val_loss: 2.1297
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.9663
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1995 - loss: 2.3851  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1986 - loss: 2.3258
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1931 - loss: 2.3020
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1901 - loss: 2.2940
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1892 - loss: 2.2883
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1880 - loss: 2.2842
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1871 - loss: 2.2815
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1866 - loss: 2.2790
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1861 - loss: 2.2777
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1859 - loss: 2.2767
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2761
[1m 311/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2756
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.2752
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.2748
[1m 389/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2743
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.2738
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.2734
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2731
[1m 500/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2728
[1m 527/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2726
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2722
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2718
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2713
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2708
[1m 662/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1856 - loss: 2.2703
[1m 689/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2698
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1857 - loss: 2.2693
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1858 - loss: 2.2687
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1858 - loss: 2.2683
[1m 791/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.2677
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.2672
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.2667
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1861 - loss: 2.2662
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.2658
[1m 924/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.2653
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.2650
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.2646
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.2643
[1m1031/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1865 - loss: 2.2639
[1m1057/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1865 - loss: 2.2636
[1m1083/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1866 - loss: 2.2632
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1866 - loss: 2.2629
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1867 - loss: 2.2625
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1867 - loss: 2.2621
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1868 - loss: 2.2620 - val_accuracy: 0.2276 - val_loss: 2.0529
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0794
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2322 - loss: 2.2531  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2278 - loss: 2.2303
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2262 - loss: 2.2111
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2233 - loss: 2.2071
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2199 - loss: 2.2028
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2175 - loss: 2.2000
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2156 - loss: 2.1987
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2144 - loss: 2.1978
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2134 - loss: 2.1981
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.1986
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2114 - loss: 2.1988
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2105 - loss: 2.1991
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2097 - loss: 2.1996
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2090 - loss: 2.2004
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2083 - loss: 2.2014
[1m 429/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2076 - loss: 2.2022
[1m 454/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2070 - loss: 2.2029
[1m 482/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2064 - loss: 2.2034
[1m 509/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2060 - loss: 2.2039
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2056 - loss: 2.2043
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2054 - loss: 2.2044
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2051 - loss: 2.2044
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2049 - loss: 2.2044
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2048 - loss: 2.2043
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2046 - loss: 2.2043
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2046 - loss: 2.2041
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2039
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2038
[1m 772/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.2037
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.2035
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.2033
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.2031
[1m 878/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.2029
[1m 906/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.2026
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2023
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2021
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2018
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2015
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2013
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2010
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2008
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2006
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.2003
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2046 - loss: 2.2001
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2046 - loss: 2.2001 - val_accuracy: 0.2592 - val_loss: 2.0076
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.9459
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2211 - loss: 2.1114  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2190 - loss: 2.1070
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2164 - loss: 2.1095
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2147 - loss: 2.1145
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2134 - loss: 2.1215
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2123 - loss: 2.1280
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2116 - loss: 2.1333
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2117 - loss: 2.1360
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2117 - loss: 2.1378
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2119 - loss: 2.1397
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2122 - loss: 2.1412
[1m 307/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2123 - loss: 2.1418
[1m 331/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2123 - loss: 2.1420
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.1424
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.1426
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.1426
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2125 - loss: 2.1425
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2126 - loss: 2.1424
[1m 480/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2126 - loss: 2.1421
[1m 503/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2127 - loss: 2.1420
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2128 - loss: 2.1419
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2128 - loss: 2.1419
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2129 - loss: 2.1419
[1m 611/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2130 - loss: 2.1420
[1m 638/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2132 - loss: 2.1420
[1m 666/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2133 - loss: 2.1420
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2134 - loss: 2.1421
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2136 - loss: 2.1421
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2137 - loss: 2.1421
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2138 - loss: 2.1421
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2138 - loss: 2.1421
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2139 - loss: 2.1421
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2140 - loss: 2.1420
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2141 - loss: 2.1419
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2142 - loss: 2.1419
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2143 - loss: 2.1418
[1m 960/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2144 - loss: 2.1418
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2145 - loss: 2.1418
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2146 - loss: 2.1417
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2147 - loss: 2.1416
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2149 - loss: 2.1415
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2150 - loss: 2.1414
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2151 - loss: 2.1412
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2153 - loss: 2.1411
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2154 - loss: 2.1410 - val_accuracy: 0.2609 - val_loss: 2.0085
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.4375 - loss: 2.1409
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2632 - loss: 2.1089  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2602 - loss: 2.1154
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2620 - loss: 2.1183
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2596 - loss: 2.1236
[1m 124/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2569 - loss: 2.1267
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2552 - loss: 2.1256
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.1245
[1m 203/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2523 - loss: 2.1242
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2514 - loss: 2.1235
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.1231
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.1220
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.1209
[1m 334/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.1197
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.1185
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2493 - loss: 2.1174
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.1162
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2488 - loss: 2.1149
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.1139
[1m 490/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2484 - loss: 2.1130
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2483 - loss: 2.1123
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2481 - loss: 2.1118
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2480 - loss: 2.1115
[1m 592/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2477 - loss: 2.1113
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2475 - loss: 2.1111
[1m 643/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2473 - loss: 2.1108
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.1105
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.1102
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2467 - loss: 2.1099
[1m 741/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.1096
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.1092
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2462 - loss: 2.1088
[1m 820/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.1085
[1m 847/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1081
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1077
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1072
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1067
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1063
[1m 984/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1058
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1053
[1m1037/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1048
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1043
[1m1090/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1039
[1m1117/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.1034
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.1030
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2461 - loss: 2.1026 - val_accuracy: 0.2444 - val_loss: 2.0038
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9020
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2397 - loss: 1.9896  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2282 - loss: 2.0146
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2272 - loss: 2.0238
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2286 - loss: 2.0291
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2321 - loss: 2.0309
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2362 - loss: 2.0304
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2388 - loss: 2.0300
[1m 210/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2412 - loss: 2.0302
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.0302
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2446 - loss: 2.0302
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2458 - loss: 2.0303
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2468 - loss: 2.0304
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2476 - loss: 2.0303
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.0302
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.0303
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0307
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.0310
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2520 - loss: 2.0314
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2526 - loss: 2.0317
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2533 - loss: 2.0320
[1m 551/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.0324
[1m 579/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.0328
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2550 - loss: 2.0332
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2555 - loss: 2.0335
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2559 - loss: 2.0338
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2563 - loss: 2.0340
[1m 712/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2568 - loss: 2.0343
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2572 - loss: 2.0345
[1m 766/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.0347
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.0348
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2586 - loss: 2.0349
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.0349
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.0350
[1m 900/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.0350
[1m 926/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.0350
[1m 950/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.0350
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2606 - loss: 2.0349
[1m1003/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.0348
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2611 - loss: 2.0346
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2613 - loss: 2.0345
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2615 - loss: 2.0344
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2617 - loss: 2.0343
[1m1132/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2620 - loss: 2.0341
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2622 - loss: 2.0340
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2623 - loss: 2.0340 - val_accuracy: 0.3164 - val_loss: 1.8726
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.1875 - loss: 2.0903
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2609 - loss: 1.9686  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2691 - loss: 1.9684
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2715 - loss: 1.9700
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2719 - loss: 1.9811
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2723 - loss: 1.9884
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2727 - loss: 1.9914
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 1.9923
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2742 - loss: 1.9927
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2752 - loss: 1.9921
[1m 268/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2760 - loss: 1.9912
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2767 - loss: 1.9905
[1m 320/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 1.9903
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2776 - loss: 1.9903
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 1.9905
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2785 - loss: 1.9907
[1m 424/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2789 - loss: 1.9908
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 1.9908
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 1.9907
[1m 504/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 1.9906
[1m 532/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 1.9903
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 1.9900
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2817 - loss: 1.9896
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2822 - loss: 1.9892
[1m 635/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2825 - loss: 1.9890
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 1.9888
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 1.9887
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 1.9887
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 1.9887
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 1.9888
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 1.9890
[1m 822/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 1.9891
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2839 - loss: 1.9892
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 1.9893
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2841 - loss: 1.9894
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2843 - loss: 1.9895
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2844 - loss: 1.9895
[1m 978/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 1.9896
[1m1002/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 1.9896
[1m1029/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 1.9895
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 1.9894
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 1.9893
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 1.9892
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 1.9890
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 1.9888
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2853 - loss: 1.9887 - val_accuracy: 0.3406 - val_loss: 1.8202
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.3750 - loss: 2.0696
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3013 - loss: 1.9807  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2867 - loss: 1.9900
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2887 - loss: 1.9748
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2892 - loss: 1.9655
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2909 - loss: 1.9571
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2931 - loss: 1.9506
[1m 174/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2950 - loss: 1.9457
[1m 200/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 1.9416
[1m 228/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 1.9376
[1m 255/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 1.9350
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 1.9337
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 1.9329
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 1.9327
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9327
[1m 386/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9330
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9333
[1m 439/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9336
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9340
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9347
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9351
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9355
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9358
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9359
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9361
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9363
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9366
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9368
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 1.9370
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9371
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 1.9372
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 1.9372
[1m 835/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 1.9372
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3012 - loss: 1.9371
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 1.9370
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 1.9369
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 1.9368
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 1.9366
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3019 - loss: 1.9365
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3021 - loss: 1.9364
[1m1046/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 1.9364
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 1.9363
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 1.9363
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 1.9363
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 1.9363
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3025 - loss: 1.9363 - val_accuracy: 0.3608 - val_loss: 1.7877
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.1689
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2679 - loss: 2.0975  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2891 - loss: 2.0129
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9922
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2993 - loss: 1.9754
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3003 - loss: 1.9655
[1m 153/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3007 - loss: 1.9577
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3015 - loss: 1.9516
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 1.9480
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 1.9463
[1m 257/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 1.9448
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 1.9435
[1m 308/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3033 - loss: 1.9422
[1m 335/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 1.9408
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9391
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9375
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9361
[1m 441/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9349
[1m 469/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9340
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9332
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9323
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9316
[1m 573/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9310
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9304
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 1.9300
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 1.9295
[1m 677/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 1.9292
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9289
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9285
[1m 759/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9280
[1m 787/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9275
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9270
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9266
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9262
[1m 896/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3038 - loss: 1.9258
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 1.9254
[1m 947/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 1.9250
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 1.9246
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9242
[1m1028/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9238
[1m1054/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9234
[1m1081/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3041 - loss: 1.9230
[1m1109/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3042 - loss: 1.9225
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3042 - loss: 1.9221
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 1.9217
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3043 - loss: 1.9216 - val_accuracy: 0.3195 - val_loss: 1.8043
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.5163
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2268 - loss: 2.0120  
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2541 - loss: 1.9819
[1m  73/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2693 - loss: 1.9661
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2788 - loss: 1.9506
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2845 - loss: 1.9400
[1m 149/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2878 - loss: 1.9346
[1m 177/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2918 - loss: 1.9288
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9237
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 1.9199
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 1.9172
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 1.9145
[1m 315/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 1.9125
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 1.9108
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 1.9096
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 1.9086
[1m 419/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 1.9079
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 1.9073
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 1.9069
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3062 - loss: 1.9067
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 1.9064
[1m 548/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3067 - loss: 1.9059
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3069 - loss: 1.9054
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 1.9050
[1m 623/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 1.9046
[1m 649/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3076 - loss: 1.9042
[1m 673/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3078 - loss: 1.9038
[1m 700/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3081 - loss: 1.9033
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3083 - loss: 1.9029
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3086 - loss: 1.9023
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3088 - loss: 1.9019
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3090 - loss: 1.9015
[1m 824/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 1.9011
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 1.9008
[1m 875/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 1.9004
[1m 899/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3097 - loss: 1.9000
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 1.8997
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3101 - loss: 1.8994
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 1.8991
[1m1000/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3104 - loss: 1.8987
[1m1026/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3106 - loss: 1.8984
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 1.8981
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8977
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 1.8973
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 1.8970
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 1.8966
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3115 - loss: 1.8964 - val_accuracy: 0.3556 - val_loss: 1.7577
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.9117
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2742 - loss: 1.8615  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2824 - loss: 1.8671
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2854 - loss: 1.8627
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2884 - loss: 1.8575
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2907 - loss: 1.8567
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2934 - loss: 1.8557
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 1.8545
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 1.8546
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 1.8546
[1m 258/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 1.8547
[1m 284/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 1.8553
[1m 312/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 1.8565
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3068 - loss: 1.8573
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3078 - loss: 1.8579
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 1.8585
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3100 - loss: 1.8590
[1m 449/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 1.8593
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 1.8595
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 1.8595
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 1.8595
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 1.8593
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 1.8590
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 1.8587
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3160 - loss: 1.8583
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 1.8579
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 1.8574
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 1.8569
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3186 - loss: 1.8565
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 1.8561
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 1.8558
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 1.8554
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 1.8551
[1m 870/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 1.8548
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3212 - loss: 1.8545
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3215 - loss: 1.8542
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3218 - loss: 1.8541
[1m 975/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 1.8539
[1m1001/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 1.8538
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 1.8536
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.8536
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3228 - loss: 1.8535
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 1.8534
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 1.8534
[1m1157/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 1.8533
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3234 - loss: 1.8532 - val_accuracy: 0.3663 - val_loss: 1.7561
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7504
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3049 - loss: 1.9313  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3271 - loss: 1.8779
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3360 - loss: 1.8465
[1m 101/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3396 - loss: 1.8328
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8259
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8232
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8211
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8216
[1m 233/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8215
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3413 - loss: 1.8211
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8210
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8207
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8209
[1m 366/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8211
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8211
[1m 415/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8211
[1m 442/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 1.8210
[1m 470/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8208
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8209
[1m 522/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8210
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3415 - loss: 1.8211
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8211
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3416 - loss: 1.8212
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8213
[1m 648/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8216
[1m 675/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8219
[1m 704/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8222
[1m 728/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8225
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8227
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8229
[1m 801/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8231
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8233
[1m 855/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8234
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8235
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8236
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8237
[1m 962/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 1.8237
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8237
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8237
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8236
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8235
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3419 - loss: 1.8233
[1m1128/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3420 - loss: 1.8232
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3420 - loss: 1.8231
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3420 - loss: 1.8230 - val_accuracy: 0.3476 - val_loss: 1.7655
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 21ms/step - accuracy: 0.3125 - loss: 2.3988
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8811  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3372 - loss: 1.8505
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3377 - loss: 1.8446
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8346
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8253
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3398 - loss: 1.8182
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8142
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3410 - loss: 1.8103
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3421 - loss: 1.8061
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3429 - loss: 1.8022
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 1.7988
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3444 - loss: 1.7969
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3452 - loss: 1.7951
[1m 371/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3459 - loss: 1.7935
[1m 398/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3466 - loss: 1.7921
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.7908
[1m 453/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3478 - loss: 1.7897
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3483 - loss: 1.7887
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3487 - loss: 1.7878
[1m 534/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3489 - loss: 1.7870
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.7863
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3494 - loss: 1.7856
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7851
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7846
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7841
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3501 - loss: 1.7837
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3502 - loss: 1.7834
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3503 - loss: 1.7831
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3504 - loss: 1.7829
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3505 - loss: 1.7827
[1m 809/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3506 - loss: 1.7825
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3507 - loss: 1.7824
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3508 - loss: 1.7823
[1m 882/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3508 - loss: 1.7822
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3508 - loss: 1.7822
[1m 935/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3509 - loss: 1.7822
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3509 - loss: 1.7821
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7820
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3511 - loss: 1.7819
[1m1039/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7819
[1m1066/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7820
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7820
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7820
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7821
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7821
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7821 - val_accuracy: 0.3800 - val_loss: 1.7510
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.4375 - loss: 1.6807
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7372  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3536 - loss: 1.7523
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7643
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3468 - loss: 1.7727
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3470 - loss: 1.7769
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7778
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.7755
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3503 - loss: 1.7724
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3509 - loss: 1.7704
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3514 - loss: 1.7691
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7684
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3524 - loss: 1.7679
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3529 - loss: 1.7671
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3532 - loss: 1.7665
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3535 - loss: 1.7656
[1m 420/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7646
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3542 - loss: 1.7637
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.7628
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3550 - loss: 1.7622
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7618
[1m 552/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3555 - loss: 1.7616
[1m 576/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3557 - loss: 1.7614
[1m 600/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3560 - loss: 1.7613
[1m 627/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3562 - loss: 1.7613
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7613
[1m 680/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7613
[1m 705/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7613
[1m 727/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.7614
[1m 754/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3571 - loss: 1.7614
[1m 778/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7613
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7613
[1m 831/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7612
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7612
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7611
[1m 909/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7611
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7611
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7610
[1m 987/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7609
[1m1013/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7608
[1m1040/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7608
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7607
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7607
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7607
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7607
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7607 - val_accuracy: 0.3558 - val_loss: 1.7791
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7397
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3814 - loss: 1.6561  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3725 - loss: 1.7251
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3679 - loss: 1.7537
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7680
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7755
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7778
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7792
[1m 220/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7792
[1m 247/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7784
[1m 275/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7783
[1m 302/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7774
[1m 330/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7761
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7750
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7740
[1m 414/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7729
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7718
[1m 468/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7703
[1m 495/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7692
[1m 521/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3582 - loss: 1.7682
[1m 547/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7673
[1m 572/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7667
[1m 601/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7661
[1m 628/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3590 - loss: 1.7655
[1m 653/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7650
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7645
[1m 706/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7640
[1m 731/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3594 - loss: 1.7636
[1m 757/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7631
[1m 784/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7626
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3596 - loss: 1.7622
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7618
[1m 852/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7613
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7608
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3600 - loss: 1.7603
[1m 930/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7598
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7593
[1m 985/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3603 - loss: 1.7589
[1m1010/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7585
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7581
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3605 - loss: 1.7578
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7574
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7571
[1m1138/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7568
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7565
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3608 - loss: 1.7564 - val_accuracy: 0.3569 - val_loss: 1.7813
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.3783
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3818 - loss: 1.8020  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3691 - loss: 1.7898
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7844
[1m 103/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7838
[1m 130/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7826
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7816
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7809
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3628 - loss: 1.7792
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7778
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3630 - loss: 1.7768
[1m 288/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7752
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3634 - loss: 1.7734
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7715
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7695
[1m 394/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7676
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7657
[1m 447/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7643
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3658 - loss: 1.7628
[1m 501/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7616
[1m 526/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3663 - loss: 1.7604
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3666 - loss: 1.7590
[1m 580/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3669 - loss: 1.7578
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3672 - loss: 1.7567
[1m 637/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3674 - loss: 1.7559
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7552
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3677 - loss: 1.7544
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7537
[1m 737/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3680 - loss: 1.7530
[1m 763/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7522
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3683 - loss: 1.7515
[1m 814/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7508
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3687 - loss: 1.7500
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3689 - loss: 1.7493
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3691 - loss: 1.7485
[1m 920/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3692 - loss: 1.7478
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7472
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7466
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7460
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7454
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3700 - loss: 1.7449
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3701 - loss: 1.7444
[1m1103/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3702 - loss: 1.7440
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3703 - loss: 1.7436
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7433
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3705 - loss: 1.7431 - val_accuracy: 0.3678 - val_loss: 1.7688
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.4743
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3280 - loss: 1.7312  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3467 - loss: 1.7300
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3526 - loss: 1.7396
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3567 - loss: 1.7397
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7375
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3618 - loss: 1.7365
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3633 - loss: 1.7346
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7329
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3655 - loss: 1.7312
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3665 - loss: 1.7293
[1m 285/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7272
[1m 310/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3691 - loss: 1.7252
[1m 332/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7239
[1m 358/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3708 - loss: 1.7221
[1m 381/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3717 - loss: 1.7203
[1m 408/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3726 - loss: 1.7184
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.7168
[1m 456/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3742 - loss: 1.7153
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3749 - loss: 1.7140
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3755 - loss: 1.7128
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3759 - loss: 1.7119
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3763 - loss: 1.7110
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3767 - loss: 1.7103
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3769 - loss: 1.7096
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3772 - loss: 1.7090
[1m 659/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3774 - loss: 1.7085
[1m 686/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3776 - loss: 1.7080
[1m 711/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.7076
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3779 - loss: 1.7073
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3780 - loss: 1.7071
[1m 793/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3780 - loss: 1.7070
[1m 819/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3781 - loss: 1.7068
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.7066
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.7064
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3784 - loss: 1.7061
[1m 922/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3784 - loss: 1.7059
[1m 949/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.7057
[1m 974/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3786 - loss: 1.7056
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3787 - loss: 1.7054
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3789 - loss: 1.7052
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3790 - loss: 1.7050
[1m1074/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3791 - loss: 1.7049
[1m1099/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3792 - loss: 1.7047
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3793 - loss: 1.7046
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3793 - loss: 1.7045
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3794 - loss: 1.7045 - val_accuracy: 0.3721 - val_loss: 1.7696
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.6974
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3185 - loss: 1.6721  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3317 - loss: 1.6957
[1m  75/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3409 - loss: 1.7102
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3475 - loss: 1.7150
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3528 - loss: 1.7126
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3569 - loss: 1.7093
[1m 180/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3598 - loss: 1.7065
[1m 204/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3616 - loss: 1.7051
[1m 227/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3631 - loss: 1.7034
[1m 252/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7004
[1m 279/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3665 - loss: 1.6967
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3680 - loss: 1.6935
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3690 - loss: 1.6913
[1m 360/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3699 - loss: 1.6894
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3706 - loss: 1.6880
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3714 - loss: 1.6867
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.6855
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3728 - loss: 1.6847
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3733 - loss: 1.6842
[1m 515/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3737 - loss: 1.6837
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3742 - loss: 1.6833
[1m 566/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3746 - loss: 1.6831
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3749 - loss: 1.6831
[1m 621/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3753 - loss: 1.6829
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3756 - loss: 1.6827
[1m 671/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3759 - loss: 1.6824
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3762 - loss: 1.6823
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.6823
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6822
[1m 768/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3768 - loss: 1.6822
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3770 - loss: 1.6823
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3772 - loss: 1.6824
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3774 - loss: 1.6825
[1m 865/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.6825
[1m 893/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6826
[1m 918/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3778 - loss: 1.6827
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3780 - loss: 1.6828
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3781 - loss: 1.6829
[1m 994/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.6830
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3784 - loss: 1.6830
[1m1048/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.6831
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3786 - loss: 1.6831
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3787 - loss: 1.6831
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3788 - loss: 1.6831
[1m1152/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3790 - loss: 1.6831
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3791 - loss: 1.6831 - val_accuracy: 0.3863 - val_loss: 1.7376
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.6250 - loss: 1.3613
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4105 - loss: 1.6322  
[1m  55/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3988 - loss: 1.6366
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3936 - loss: 1.6421
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3917 - loss: 1.6444
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6458
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3907 - loss: 1.6470
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3909 - loss: 1.6495
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3912 - loss: 1.6513
[1m 236/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3919 - loss: 1.6527
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3925 - loss: 1.6538
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3930 - loss: 1.6540
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3934 - loss: 1.6546
[1m 339/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3936 - loss: 1.6557
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3938 - loss: 1.6566
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3940 - loss: 1.6575
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3941 - loss: 1.6584
[1m 445/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3942 - loss: 1.6591
[1m 473/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3943 - loss: 1.6597
[1m 498/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3944 - loss: 1.6601
[1m 524/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3945 - loss: 1.6605
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3947 - loss: 1.6608
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3948 - loss: 1.6610
[1m 599/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3950 - loss: 1.6611
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3952 - loss: 1.6613
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6616
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6617
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3956 - loss: 1.6618
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3957 - loss: 1.6618
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3958 - loss: 1.6619
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3959 - loss: 1.6620
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3959 - loss: 1.6621
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3959 - loss: 1.6623
[1m 872/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3959 - loss: 1.6624
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6625
[1m 925/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6626
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6627
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6627
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6628
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6628
[1m1059/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6628
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6627
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3962 - loss: 1.6627
[1m1140/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6627
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6628
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6628 - val_accuracy: 0.3674 - val_loss: 1.7458

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 1s/step
[1m44/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 15:59:04.227820: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 14ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:30[0m 1s/step
[1m 48/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m106/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 955us/step
[1m162/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 936us/step
[1m216/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 935us/step
[1m274/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 922us/step
[1m333/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 909us/step
[1m386/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 915us/step
[1m438/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 921us/step
[1m493/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 920us/step
[1m546/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 923us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 967us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 56/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 932us/step
[1m112/169[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 917us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 37.65 [%]
Global F1 score (validation) = 33.83 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.17271125 0.17692621 0.16117586 ... 0.03198281 0.14555661 0.06347485]
 [0.22962533 0.22219434 0.21228671 ... 0.00279519 0.18959218 0.03005333]
 [0.23339668 0.2300191  0.21308547 ... 0.00300215 0.17870493 0.0267878 ]
 ...
 [0.23506817 0.2268673  0.20461376 ... 0.00139624 0.1791262  0.01657325]
 [0.21925189 0.22708714 0.19243653 ... 0.0083163  0.16763513 0.02252255]
 [0.19540161 0.25918174 0.17588626 ... 0.00537488 0.13766532 0.01199309]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.39 [%]
Global accuracy score (test) = 34.78 [%]
Global F1 score (train) = 42.11 [%]
Global F1 score (test) = 31.98 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.19      0.38      0.25       184
 CAMINAR CON MÓVIL O LIBRO       0.20      0.41      0.27       184
       CAMINAR USUAL SPEED       0.00      0.00      0.00       184
            CAMINAR ZIGZAG       0.59      0.33      0.42       184
          DE PIE BARRIENDO       0.34      0.41      0.37       184
   DE PIE DOBLANDO TOALLAS       0.47      0.10      0.16       184
    DE PIE MOVIENDO LIBROS       0.33      0.62      0.43       184
          DE PIE USANDO PC       0.32      0.62      0.42       184
        FASE REPOSO CON K5       0.83      0.50      0.62       184
INCREMENTAL CICLOERGOMETRO       0.74      0.50      0.60       184
           SENTADO LEYENDO       0.29      0.47      0.36       184
         SENTADO USANDO PC       0.37      0.28      0.32       184
      SENTADO VIENDO LA TV       0.00      0.00      0.00       184
   SUBIR Y BAJAR ESCALERAS       0.62      0.05      0.10       184
                    TROTAR       0.41      0.57      0.47       161

                  accuracy                           0.35      2737
                 macro avg       0.38      0.35      0.32      2737
              weighted avg       0.38      0.35      0.32      2737


Accuracy capturado en la ejecución 28: 34.78 [%]
F1-score capturado en la ejecución 28: 31.98 [%]

=== EJECUCIÓN 29 ===

--- TRAIN (ejecución 29) ---

--- TEST (ejecución 29) ---
2025-10-31 15:59:17.494198: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2025-10-31 15:59:17.505426: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1761922757.518497 1737695 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1761922757.522697 1737695 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1761922757.532648 1737695 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922757.532679 1737695 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922757.532681 1737695 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1761922757.532683 1737695 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-10-31 15:59:17.535803: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
I0000 00:00:1761922759.908065 1737695 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13750 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 4060 Ti, pci bus id: 0000:65:00.0, compute capability: 8.9
1 GPU(s) detected and VRAM set to crossover mode..
Epoch 1/21
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1761922762.971036 1737842 service.cc:152] XLA service 0x796538006c80 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1761922762.971105 1737842 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-10-31 15:59:23.042001: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.
I0000 00:00:1761922763.490474 1737842 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1761922766.129808 1737842 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46:33[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.9509
[1m  21/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.0608 - loss: 3.4613        
[1m  47/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0645 - loss: 3.4162
[1m  74/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0673 - loss: 3.3860
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0706 - loss: 3.3617
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0726 - loss: 3.3444
[1m 155/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0743 - loss: 3.3246
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0757 - loss: 3.3082
[1m 207/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0770 - loss: 3.2930
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0787 - loss: 3.2772
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0802 - loss: 3.2624
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0816 - loss: 3.2486
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0828 - loss: 3.2366
[1m 340/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0841 - loss: 3.2248
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0851 - loss: 3.2141
[1m 391/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0862 - loss: 3.2023
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0873 - loss: 3.1912
[1m 446/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0884 - loss: 3.1802
[1m 474/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0893 - loss: 3.1698
[1m 497/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0901 - loss: 3.1614
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0909 - loss: 3.1518
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0916 - loss: 3.1437
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0924 - loss: 3.1353
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0932 - loss: 3.1269
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0940 - loss: 3.1182
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0946 - loss: 3.1113
[1m 681/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0952 - loss: 3.1041
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0958 - loss: 3.0968
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0965 - loss: 3.0894
[1m 760/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0970 - loss: 3.0832
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0977 - loss: 3.0761
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0983 - loss: 3.0700
[1m 837/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0988 - loss: 3.0643
[1m 863/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0994 - loss: 3.0583
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1000 - loss: 3.0520
[1m 917/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1005 - loss: 3.0463
[1m 944/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1010 - loss: 3.0406
[1m 971/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1015 - loss: 3.0349
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1020 - loss: 3.0299
[1m1023/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1025 - loss: 3.0242
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1030 - loss: 3.0191
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1035 - loss: 3.0138
[1m1102/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1040 - loss: 3.0089
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1045 - loss: 3.0038
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1049 - loss: 2.9989
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1051 - loss: 2.9967
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m13s[0m 6ms/step - accuracy: 0.1051 - loss: 2.9965 - val_accuracy: 0.1930 - val_loss: 2.2530
Epoch 2/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.0625 - loss: 2.4841
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1609 - loss: 2.4263  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1594 - loss: 2.4311
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1594 - loss: 2.4336
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1607 - loss: 2.4368
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1616 - loss: 2.4396
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1620 - loss: 2.4437
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1621 - loss: 2.4482
[1m 208/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1615 - loss: 2.4523
[1m 234/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1608 - loss: 2.4559
[1m 261/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1600 - loss: 2.4589
[1m 287/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1594 - loss: 2.4608
[1m 314/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1587 - loss: 2.4627
[1m 341/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1581 - loss: 2.4641
[1m 369/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1577 - loss: 2.4652
[1m 397/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4657
[1m 425/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1572 - loss: 2.4660
[1m 450/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1571 - loss: 2.4662
[1m 478/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1569 - loss: 2.4666
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1569 - loss: 2.4669
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1569 - loss: 2.4668
[1m 554/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1570 - loss: 2.4667
[1m 577/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1570 - loss: 2.4664
[1m 602/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1571 - loss: 2.4661
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1571 - loss: 2.4657
[1m 657/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1571 - loss: 2.4654
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1571 - loss: 2.4651
[1m 709/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1571 - loss: 2.4648
[1m 736/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1571 - loss: 2.4644
[1m 762/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1571 - loss: 2.4642
[1m 789/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1572 - loss: 2.4638
[1m 816/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1572 - loss: 2.4634
[1m 843/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1572 - loss: 2.4630
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1573 - loss: 2.4625
[1m 897/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1573 - loss: 2.4620
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1573 - loss: 2.4615
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4609
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4604
[1m1006/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4598
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4593
[1m1058/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4587
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1574 - loss: 2.4580
[1m1116/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1575 - loss: 2.4573
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1575 - loss: 2.4566
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1575 - loss: 2.4560 - val_accuracy: 0.2126 - val_loss: 2.1517
Epoch 3/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.0625 - loss: 2.4933
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1479 - loss: 2.4789  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1556 - loss: 2.4389
[1m  82/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1573 - loss: 2.4183
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1561 - loss: 2.4083
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1569 - loss: 2.4007
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1574 - loss: 2.3942
[1m 185/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1581 - loss: 2.3892
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1587 - loss: 2.3849
[1m 239/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1591 - loss: 2.3816
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1596 - loss: 2.3787
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1601 - loss: 2.3754
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1605 - loss: 2.3726
[1m 343/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1609 - loss: 2.3704
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1613 - loss: 2.3681
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1616 - loss: 2.3658
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1620 - loss: 2.3638
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1623 - loss: 2.3622
[1m 484/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1626 - loss: 2.3604
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1629 - loss: 2.3591
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1631 - loss: 2.3578
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1634 - loss: 2.3567
[1m 588/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1635 - loss: 2.3558
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1637 - loss: 2.3550
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1639 - loss: 2.3542
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1641 - loss: 2.3533
[1m 695/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1643 - loss: 2.3526
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1645 - loss: 2.3520
[1m 743/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1646 - loss: 2.3514
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1648 - loss: 2.3507
[1m 794/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1650 - loss: 2.3501
[1m 821/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1652 - loss: 2.3495
[1m 848/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1654 - loss: 2.3489
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1656 - loss: 2.3483
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1657 - loss: 2.3477
[1m 927/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1659 - loss: 2.3472
[1m 952/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1660 - loss: 2.3466
[1m 977/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1661 - loss: 2.3460
[1m1004/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1663 - loss: 2.3454
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1665 - loss: 2.3448
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1666 - loss: 2.3441
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1668 - loss: 2.3435
[1m1113/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1670 - loss: 2.3429
[1m1141/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1672 - loss: 2.3423
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1673 - loss: 2.3416 - val_accuracy: 0.2167 - val_loss: 2.0905
Epoch 4/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2754
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1943 - loss: 2.1530  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1865 - loss: 2.1737
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1824 - loss: 2.1871
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1812 - loss: 2.1912
[1m 128/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1799 - loss: 2.1958
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1790 - loss: 2.2022
[1m 179/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1789 - loss: 2.2072
[1m 206/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1793 - loss: 2.2107
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1797 - loss: 2.2138
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1802 - loss: 2.2158
[1m 282/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1804 - loss: 2.2181
[1m 309/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1805 - loss: 2.2205
[1m 337/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1806 - loss: 2.2225
[1m 363/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1807 - loss: 2.2241
[1m 388/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1807 - loss: 2.2256
[1m 412/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1807 - loss: 2.2269
[1m 437/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1809 - loss: 2.2282
[1m 464/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1811 - loss: 2.2294
[1m 489/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1813 - loss: 2.2302
[1m 517/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.2307
[1m 543/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1820 - loss: 2.2311
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.2317
[1m 594/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.2321
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1828 - loss: 2.2325
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1831 - loss: 2.2329
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1833 - loss: 2.2334
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2339
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.2343
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.2347
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1836 - loss: 2.2351
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1837 - loss: 2.2355
[1m 830/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1838 - loss: 2.2357
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1838 - loss: 2.2360
[1m 884/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1839 - loss: 2.2362
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1840 - loss: 2.2364
[1m 939/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1841 - loss: 2.2366
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1842 - loss: 2.2367
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1842 - loss: 2.2367
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1843 - loss: 2.2368
[1m1051/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1844 - loss: 2.2368
[1m1080/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1844 - loss: 2.2368
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1845 - loss: 2.2368
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.2367
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2366
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1847 - loss: 2.2366 - val_accuracy: 0.2122 - val_loss: 2.0427
Epoch 5/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 22ms/step - accuracy: 0.0625 - loss: 2.3259
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1854 - loss: 2.2273  
[1m  56/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1901 - loss: 2.2126
[1m  83/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1898 - loss: 2.2158
[1m 110/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1905 - loss: 2.2149
[1m 138/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1910 - loss: 2.2136
[1m 165/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1917 - loss: 2.2123
[1m 191/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1921 - loss: 2.2111
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1921 - loss: 2.2103
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1921 - loss: 2.2093
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1924 - loss: 2.2085
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1926 - loss: 2.2077
[1m 322/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1928 - loss: 2.2069
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1931 - loss: 2.2061
[1m 379/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1934 - loss: 2.2055
[1m 406/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1937 - loss: 2.2052
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1940 - loss: 2.2050
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1942 - loss: 2.2050
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1944 - loss: 2.2049
[1m 511/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1946 - loss: 2.2047
[1m 537/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1949 - loss: 2.2044
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1952 - loss: 2.2042
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1953 - loss: 2.2040
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1955 - loss: 2.2038
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1958 - loss: 2.2036
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1960 - loss: 2.2035
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1962 - loss: 2.2033
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1964 - loss: 2.2030
[1m 752/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1966 - loss: 2.2027
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1968 - loss: 2.2025
[1m 805/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1970 - loss: 2.2023
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1972 - loss: 2.2019
[1m 860/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1974 - loss: 2.2016
[1m 889/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1976 - loss: 2.2013
[1m 914/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1977 - loss: 2.2009
[1m 942/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1979 - loss: 2.2006
[1m 969/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1980 - loss: 2.2003
[1m 996/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1981 - loss: 2.2000
[1m1022/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1982 - loss: 2.1998
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.1995
[1m1075/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1984 - loss: 2.1993
[1m1101/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1985 - loss: 2.1990
[1m1126/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1986 - loss: 2.1987
[1m1153/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1988 - loss: 2.1984
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1988 - loss: 2.1982 - val_accuracy: 0.2424 - val_loss: 2.0015
Epoch 6/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9942
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2256 - loss: 2.1123  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2299 - loss: 2.1054
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2277 - loss: 2.1025
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2252 - loss: 2.1025
[1m 127/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2232 - loss: 2.1051
[1m 154/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2232 - loss: 2.1073
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2231 - loss: 2.1102
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2229 - loss: 2.1133
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2232 - loss: 2.1147
[1m 263/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1156
[1m 289/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1163
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1169
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1174
[1m 367/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2234 - loss: 2.1181
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2234 - loss: 2.1191
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2233 - loss: 2.1201
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2234 - loss: 2.1211
[1m 475/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1218
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1225
[1m 530/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2237 - loss: 2.1232
[1m 555/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2238 - loss: 2.1238
[1m 584/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2237 - loss: 2.1248
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2237 - loss: 2.1254
[1m 632/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2237 - loss: 2.1262
[1m 658/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1267
[1m 683/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1272
[1m 710/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1276
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1279
[1m 764/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1282
[1m 790/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1285
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1287
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1290
[1m 873/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1293
[1m 901/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1297
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1300
[1m 957/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1303
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1306
[1m1009/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1308
[1m1036/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1310
[1m1064/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1311
[1m1091/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.1313
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.1313
[1m1145/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2237 - loss: 2.1313
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2237 - loss: 2.1313 - val_accuracy: 0.2768 - val_loss: 1.9648
Epoch 7/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7993
[1m  23/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2606 - loss: 2.0155  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2576 - loss: 2.0389
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2523 - loss: 2.0598
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2505 - loss: 2.0671
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2503 - loss: 2.0699
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.0711
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2506 - loss: 2.0724
[1m 205/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2503 - loss: 2.0746
[1m 232/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.0774
[1m 260/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2492 - loss: 2.0794
[1m 286/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2488 - loss: 2.0808
[1m 313/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.0820
[1m 338/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2485 - loss: 2.0833
[1m 365/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.0845
[1m 392/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.0855
[1m 418/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2487 - loss: 2.0861
[1m 444/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2488 - loss: 2.0865
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2489 - loss: 2.0868
[1m 496/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.0867
[1m 525/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.0866
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.0864
[1m 582/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.0864
[1m 608/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.0863
[1m 636/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.0861
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2491 - loss: 2.0859
[1m 687/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2491 - loss: 2.0859
[1m 716/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.0858
[1m 745/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.0857
[1m 773/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2493 - loss: 2.0856
[1m 799/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2494 - loss: 2.0854
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2495 - loss: 2.0851
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2497 - loss: 2.0849
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2498 - loss: 2.0845
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2499 - loss: 2.0842
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2501 - loss: 2.0838
[1m 963/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2503 - loss: 2.0835
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2504 - loss: 2.0832
[1m1015/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2506 - loss: 2.0830
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2508 - loss: 2.0826
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2510 - loss: 2.0823
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.0819
[1m1125/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2514 - loss: 2.0816
[1m1151/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2516 - loss: 2.0812
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2517 - loss: 2.0810 - val_accuracy: 0.3060 - val_loss: 1.9112
Epoch 8/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.9849
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2882 - loss: 2.0298  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2912 - loss: 2.0218
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2889 - loss: 2.0198
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2873 - loss: 2.0200
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.0222
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.0236
[1m 189/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 2.0256
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2829 - loss: 2.0267
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.0283
[1m 264/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2809 - loss: 2.0294
[1m 290/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.0300
[1m 316/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.0301
[1m 342/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2786 - loss: 2.0300
[1m 370/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 2.0299
[1m 399/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2775 - loss: 2.0296
[1m 426/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2771 - loss: 2.0292
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2766 - loss: 2.0286
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2763 - loss: 2.0281
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2760 - loss: 2.0275
[1m 536/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2759 - loss: 2.0269
[1m 564/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 2.0264
[1m 591/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2757 - loss: 2.0262
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 2.0261
[1m 644/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2755 - loss: 2.0259
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2754 - loss: 2.0259
[1m 696/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2753 - loss: 2.0258
[1m 724/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2752 - loss: 2.0257
[1m 751/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2751 - loss: 2.0256
[1m 779/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2750 - loss: 2.0255
[1m 807/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2748 - loss: 2.0254
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2747 - loss: 2.0253
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2746 - loss: 2.0253
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2745 - loss: 2.0252
[1m 912/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2744 - loss: 2.0252
[1m 940/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2743 - loss: 2.0252
[1m 968/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.0252
[1m 995/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.0251
[1m1021/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0250
[1m1049/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0249
[1m1076/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0248
[1m1104/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0246
[1m1131/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0244
[1m1156/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0242
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2740 - loss: 2.0241 - val_accuracy: 0.3269 - val_loss: 1.8877
Epoch 9/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 1.9214
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3011 - loss: 1.8938  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3012 - loss: 1.9323
[1m  72/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3005 - loss: 1.9413
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3021 - loss: 1.9447
[1m 129/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3011 - loss: 1.9472
[1m 157/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 1.9498
[1m 184/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 1.9507
[1m 213/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 1.9513
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 1.9527
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9535
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9542
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9546
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9546
[1m 373/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9544
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2950 - loss: 1.9543
[1m 427/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2948 - loss: 1.9543
[1m 452/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9543
[1m 479/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9542
[1m 505/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9541
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9543
[1m 561/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9545
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9547
[1m 617/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 1.9550
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 1.9552
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 1.9554
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9555
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9557
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9559
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9561
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2948 - loss: 1.9564
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2948 - loss: 1.9565
[1m 857/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 1.9567
[1m 879/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 1.9568
[1m 904/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 1.9570
[1m 933/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9572
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9575
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9577
[1m1012/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9579
[1m1041/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9582
[1m1070/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9585
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9587
[1m1123/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9589
[1m1148/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9591
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9592 - val_accuracy: 0.3271 - val_loss: 1.8372
Epoch 10/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1964
[1m  27/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2981 - loss: 1.9410  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2955 - loss: 1.9347
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9269
[1m 108/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2937 - loss: 1.9279
[1m 136/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 1.9305
[1m 162/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9319
[1m 190/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 1.9328
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 1.9338
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2911 - loss: 1.9355
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2913 - loss: 1.9367
[1m 298/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 1.9377
[1m 326/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 1.9386
[1m 354/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2915 - loss: 1.9390
[1m 382/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2916 - loss: 1.9395
[1m 407/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2916 - loss: 1.9399
[1m 434/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 1.9400
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2919 - loss: 1.9400
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2920 - loss: 1.9401
[1m 519/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2922 - loss: 1.9403
[1m 546/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 1.9401
[1m 574/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 1.9399
[1m 605/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2929 - loss: 1.9395
[1m 631/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 1.9391
[1m 661/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2935 - loss: 1.9386
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2938 - loss: 1.9383
[1m 718/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 1.9380
[1m 746/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 1.9377
[1m 771/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 1.9374
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 1.9370
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 1.9367
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2947 - loss: 1.9364
[1m 880/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 1.9362
[1m 907/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 1.9359
[1m 934/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 1.9356
[1m 961/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 1.9353
[1m 988/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 1.9350
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 1.9347
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 1.9343
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2957 - loss: 1.9340
[1m1096/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 1.9336
[1m1121/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 1.9332
[1m1147/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2962 - loss: 1.9329
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2963 - loss: 1.9326 - val_accuracy: 0.3291 - val_loss: 1.8018
Epoch 11/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.6589
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3359 - loss: 1.8086  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3349 - loss: 1.8246
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3325 - loss: 1.8382
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3304 - loss: 1.8474
[1m 137/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 1.8516
[1m 166/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3298 - loss: 1.8539
[1m 195/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 1.8551
[1m 225/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3289 - loss: 1.8564
[1m 250/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3290 - loss: 1.8564
[1m 278/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 1.8562
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3293 - loss: 1.8566
[1m 336/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3293 - loss: 1.8575
[1m 364/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3291 - loss: 1.8583
[1m 393/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3289 - loss: 1.8589
[1m 416/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3286 - loss: 1.8597
[1m 443/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3283 - loss: 1.8605
[1m 471/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3282 - loss: 1.8611
[1m 499/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 1.8618
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3280 - loss: 1.8626
[1m 553/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3279 - loss: 1.8632
[1m 581/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3278 - loss: 1.8638
[1m 607/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3277 - loss: 1.8645
[1m 633/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 1.8651
[1m 663/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3274 - loss: 1.8659
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3272 - loss: 1.8666
[1m 721/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 1.8673
[1m 748/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 1.8679
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 1.8685
[1m 804/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3264 - loss: 1.8690
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 1.8695
[1m 861/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3261 - loss: 1.8699
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 1.8705
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 1.8709
[1m 943/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 1.8712
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3253 - loss: 1.8717
[1m 999/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 1.8722
[1m1027/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 1.8726
[1m1050/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 1.8730
[1m1077/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3245 - loss: 1.8734
[1m1105/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3243 - loss: 1.8738
[1m1133/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 1.8742
[1m1162/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 1.8745
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3239 - loss: 1.8746 - val_accuracy: 0.3484 - val_loss: 1.7862
Epoch 12/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.8129
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3538 - loss: 1.8836  
[1m  50/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3586 - loss: 1.8504
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3516 - loss: 1.8554
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3437 - loss: 1.8614
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.8668
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8694
[1m 188/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.8710
[1m 216/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3314 - loss: 1.8708
[1m 244/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3308 - loss: 1.8694
[1m 272/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8678
[1m 299/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3304 - loss: 1.8669
[1m 327/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8659
[1m 356/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 1.8650
[1m 385/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 1.8641
[1m 411/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3303 - loss: 1.8634
[1m 438/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3301 - loss: 1.8631
[1m 466/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3299 - loss: 1.8627
[1m 492/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 1.8623
[1m 520/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3295 - loss: 1.8621
[1m 549/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3293 - loss: 1.8619
[1m 575/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 1.8615
[1m 604/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3291 - loss: 1.8611
[1m 629/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3291 - loss: 1.8607
[1m 654/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3290 - loss: 1.8602
[1m 684/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3290 - loss: 1.8596
[1m 714/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3290 - loss: 1.8590
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3290 - loss: 1.8585
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3289 - loss: 1.8580
[1m 797/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3289 - loss: 1.8576
[1m 825/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3289 - loss: 1.8571
[1m 853/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3289 - loss: 1.8567
[1m 877/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8564
[1m 902/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8561
[1m 931/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3288 - loss: 1.8559
[1m 958/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3287 - loss: 1.8557
[1m 983/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3287 - loss: 1.8556
[1m1011/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3287 - loss: 1.8554
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3286 - loss: 1.8552
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3286 - loss: 1.8551
[1m1092/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3285 - loss: 1.8551
[1m1118/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8551
[1m1144/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.8550
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3283 - loss: 1.8549 - val_accuracy: 0.3499 - val_loss: 1.7956
Epoch 13/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.7010
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3432 - loss: 1.7654  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3498 - loss: 1.7779
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3486 - loss: 1.7904
[1m 107/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3486 - loss: 1.7985
[1m 133/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.8076
[1m 159/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3458 - loss: 1.8122
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3442 - loss: 1.8170
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3429 - loss: 1.8203
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3418 - loss: 1.8229
[1m 271/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.8248
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 1.8257
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.8263
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.8271
[1m 378/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8278
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8283
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8284
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3386 - loss: 1.8285
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.8287
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.8287
[1m 533/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.8287
[1m 559/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8288
[1m 585/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.8287
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.8285
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3388 - loss: 1.8282
[1m 668/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.8278
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8276
[1m 720/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.8273
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8272
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.8269
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8267
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.8266
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8265
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.8265
[1m 910/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8264
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8264
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.8265
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8265
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8265
[1m1042/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8266
[1m1068/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8266
[1m1094/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8266
[1m1119/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8266
[1m1142/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8265
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8265
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3395 - loss: 1.8265 - val_accuracy: 0.3549 - val_loss: 1.7774
Epoch 14/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.5000 - loss: 1.6907
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3349 - loss: 1.7835  
[1m  49/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8058
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3339 - loss: 1.8142
[1m 100/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8145
[1m 126/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3343 - loss: 1.8165
[1m 152/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3332 - loss: 1.8177
[1m 181/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 1.8182
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8180
[1m 237/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8181
[1m 265/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3309 - loss: 1.8181
[1m 292/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3310 - loss: 1.8177
[1m 318/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8171
[1m 345/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3310 - loss: 1.8168
[1m 372/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3310 - loss: 1.8162
[1m 396/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.8155
[1m 422/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 1.8147
[1m 451/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 1.8141
[1m 477/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3314 - loss: 1.8137
[1m 502/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8134
[1m 529/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8133
[1m 556/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3315 - loss: 1.8132
[1m 583/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8131
[1m 609/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 1.8128
[1m 634/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.8126
[1m 660/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3318 - loss: 1.8123
[1m 688/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3319 - loss: 1.8120
[1m 715/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3321 - loss: 1.8118
[1m 738/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3322 - loss: 1.8116
[1m 765/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3324 - loss: 1.8113
[1m 792/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3326 - loss: 1.8111
[1m 818/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3328 - loss: 1.8109
[1m 845/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3330 - loss: 1.8108
[1m 871/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3331 - loss: 1.8106
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3334 - loss: 1.8104
[1m 923/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.8102
[1m 951/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3338 - loss: 1.8100
[1m 979/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3340 - loss: 1.8099
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3342 - loss: 1.8098
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3344 - loss: 1.8096
[1m1060/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3346 - loss: 1.8095
[1m1086/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3347 - loss: 1.8094
[1m1111/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3349 - loss: 1.8093
[1m1137/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3350 - loss: 1.8091
[1m1164/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3352 - loss: 1.8089
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3353 - loss: 1.8089 - val_accuracy: 0.3724 - val_loss: 1.7597
Epoch 15/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9577
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3485 - loss: 1.7422  
[1m  54/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3533 - loss: 1.7891
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3568 - loss: 1.7944
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7982
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7973
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7941
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7909
[1m 214/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7890
[1m 242/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7879
[1m 270/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3636 - loss: 1.7882
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3629 - loss: 1.7879
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3622 - loss: 1.7870
[1m 352/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3615 - loss: 1.7857
[1m 380/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3610 - loss: 1.7844
[1m 409/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3606 - loss: 1.7830
[1m 435/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3604 - loss: 1.7819
[1m 462/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3602 - loss: 1.7810
[1m 491/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3599 - loss: 1.7802
[1m 516/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3597 - loss: 1.7797
[1m 544/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7792
[1m 569/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.7788
[1m 597/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3592 - loss: 1.7785
[1m 626/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.7781
[1m 655/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7777
[1m 682/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3588 - loss: 1.7773
[1m 708/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3587 - loss: 1.7770
[1m 734/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3586 - loss: 1.7767
[1m 761/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.7764
[1m 788/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3584 - loss: 1.7762
[1m 813/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7759
[1m 840/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3581 - loss: 1.7757
[1m 868/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3580 - loss: 1.7756
[1m 898/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3579 - loss: 1.7754
[1m 928/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3578 - loss: 1.7753
[1m 953/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3577 - loss: 1.7752
[1m 980/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7751
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7750
[1m1035/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7750
[1m1056/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3575 - loss: 1.7749
[1m1082/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7747
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7746
[1m1135/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3574 - loss: 1.7745
[1m1163/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7743
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3573 - loss: 1.7743 - val_accuracy: 0.3632 - val_loss: 1.7966
Epoch 16/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.5305
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2952 - loss: 1.8031  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2977 - loss: 1.8219
[1m  79/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3097 - loss: 1.8124
[1m 106/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3175 - loss: 1.8015
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3229 - loss: 1.7948
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3284 - loss: 1.7906
[1m 186/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 1.7880
[1m 212/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.7859
[1m 240/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 1.7839
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3371 - loss: 1.7821
[1m 295/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.7801
[1m 323/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 1.7784
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3412 - loss: 1.7769
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.7752
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3430 - loss: 1.7737
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 1.7724
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3444 - loss: 1.7710
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.7698
[1m 510/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3456 - loss: 1.7688
[1m 538/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3461 - loss: 1.7678
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3466 - loss: 1.7669
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3470 - loss: 1.7664
[1m 616/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3474 - loss: 1.7658
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3478 - loss: 1.7651
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3482 - loss: 1.7645
[1m 697/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3486 - loss: 1.7638
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3489 - loss: 1.7633
[1m 750/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.7628
[1m 774/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3495 - loss: 1.7624
[1m 800/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3497 - loss: 1.7619
[1m 826/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3500 - loss: 1.7615
[1m 850/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3503 - loss: 1.7611
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3506 - loss: 1.7608
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3508 - loss: 1.7605
[1m 929/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7602
[1m 956/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.7600
[1m 981/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3513 - loss: 1.7598
[1m1007/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3515 - loss: 1.7597
[1m1032/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3516 - loss: 1.7595
[1m1061/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.7594
[1m1087/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.7593
[1m1115/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.7592
[1m1143/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.7591
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7590 - val_accuracy: 0.3680 - val_loss: 1.7751
Epoch 17/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.9462
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3810 - loss: 1.8666  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3733 - loss: 1.8331
[1m  80/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3709 - loss: 1.8089
[1m 109/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3680 - loss: 1.7917
[1m 135/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3659 - loss: 1.7827
[1m 163/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3651 - loss: 1.7737
[1m 192/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7673
[1m 217/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7638
[1m 241/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3643 - loss: 1.7602
[1m 267/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7570
[1m 297/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7539
[1m 324/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7519
[1m 351/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7504
[1m 376/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7494
[1m 403/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7486
[1m 432/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7477
[1m 458/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3650 - loss: 1.7470
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7463
[1m 514/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7458
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7454
[1m 565/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7452
[1m 589/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7450
[1m 614/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7446
[1m 639/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7442
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7438
[1m 694/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7435
[1m 719/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7433
[1m 747/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7430
[1m 777/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7429
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7428
[1m 833/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7429
[1m 862/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7430
[1m 891/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7430
[1m 919/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7431
[1m 945/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7431
[1m 972/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7432
[1m 998/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7432
[1m1025/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.7431
[1m1053/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.7430
[1m1079/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3646 - loss: 1.7429
[1m1107/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7428
[1m1136/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7427
[1m1161/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.7425
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3649 - loss: 1.7425 - val_accuracy: 0.3523 - val_loss: 1.8291
Epoch 18/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.7668
[1m  26/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3348 - loss: 1.7499  
[1m  52/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3418 - loss: 1.7441
[1m  76/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3467 - loss: 1.7381
[1m 102/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3499 - loss: 1.7369
[1m 125/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3510 - loss: 1.7401
[1m 151/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3520 - loss: 1.7418
[1m 175/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3527 - loss: 1.7428
[1m 202/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3539 - loss: 1.7419
[1m 229/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3552 - loss: 1.7397
[1m 256/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3565 - loss: 1.7379
[1m 283/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.7363
[1m 306/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3583 - loss: 1.7354
[1m 333/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.7349
[1m 361/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3595 - loss: 1.7345
[1m 387/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3601 - loss: 1.7338
[1m 413/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3607 - loss: 1.7329
[1m 440/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3613 - loss: 1.7318
[1m 465/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3619 - loss: 1.7307
[1m 493/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3626 - loss: 1.7298
[1m 518/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.7290
[1m 545/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3638 - loss: 1.7284
[1m 571/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3642 - loss: 1.7278
[1m 598/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3647 - loss: 1.7270
[1m 625/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3652 - loss: 1.7262
[1m 652/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3656 - loss: 1.7254
[1m 678/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3660 - loss: 1.7247
[1m 702/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3664 - loss: 1.7241
[1m 729/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3667 - loss: 1.7234
[1m 755/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3670 - loss: 1.7228
[1m 783/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3673 - loss: 1.7222
[1m 808/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3675 - loss: 1.7216
[1m 834/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3678 - loss: 1.7211
[1m 859/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3680 - loss: 1.7206
[1m 886/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3682 - loss: 1.7202
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3685 - loss: 1.7198
[1m 938/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3687 - loss: 1.7194
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3688 - loss: 1.7191
[1m 990/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3690 - loss: 1.7188
[1m1018/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3692 - loss: 1.7184
[1m1044/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3693 - loss: 1.7182
[1m1071/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3694 - loss: 1.7179
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3695 - loss: 1.7175
[1m1124/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3697 - loss: 1.7173
[1m1150/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3698 - loss: 1.7170
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3699 - loss: 1.7168 - val_accuracy: 0.3815 - val_loss: 1.7521
Epoch 19/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.6412
[1m  28/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3863 - loss: 1.6869  
[1m  53/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3769 - loss: 1.6809
[1m  81/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3732 - loss: 1.6798
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3733 - loss: 1.6810
[1m 131/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3734 - loss: 1.6843
[1m 156/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3740 - loss: 1.6849
[1m 182/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3752 - loss: 1.6844
[1m 209/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3761 - loss: 1.6851
[1m 235/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3763 - loss: 1.6866
[1m 262/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3768 - loss: 1.6873
[1m 291/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3771 - loss: 1.6876
[1m 319/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3775 - loss: 1.6876
[1m 346/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3778 - loss: 1.6875
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3780 - loss: 1.6877
[1m 401/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3781 - loss: 1.6884
[1m 430/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3783 - loss: 1.6891
[1m 457/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.6897
[1m 481/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.6901
[1m 508/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.6905
[1m 535/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3787 - loss: 1.6908
[1m 560/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3787 - loss: 1.6910
[1m 586/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3788 - loss: 1.6911
[1m 613/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3789 - loss: 1.6910
[1m 641/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.6909
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3793 - loss: 1.6906
[1m 692/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3795 - loss: 1.6904
[1m 717/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3797 - loss: 1.6901
[1m 744/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3800 - loss: 1.6899
[1m 770/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3802 - loss: 1.6896
[1m 798/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3804 - loss: 1.6893
[1m 823/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3806 - loss: 1.6891
[1m 849/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3808 - loss: 1.6889
[1m 876/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3810 - loss: 1.6887
[1m 903/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3812 - loss: 1.6885
[1m 932/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3813 - loss: 1.6882
[1m 959/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3815 - loss: 1.6880
[1m 986/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3816 - loss: 1.6879
[1m1014/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3817 - loss: 1.6877
[1m1038/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3819 - loss: 1.6876
[1m1065/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3820 - loss: 1.6874
[1m1093/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3821 - loss: 1.6873
[1m1120/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3822 - loss: 1.6872
[1m1146/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3823 - loss: 1.6872
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3824 - loss: 1.6871 - val_accuracy: 0.3758 - val_loss: 1.7887
Epoch 20/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.6029
[1m  24/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3952 - loss: 1.6064  
[1m  48/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3868 - loss: 1.6439
[1m  77/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3791 - loss: 1.6643
[1m 104/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3754 - loss: 1.6773
[1m 134/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3726 - loss: 1.6853
[1m 160/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3711 - loss: 1.6899
[1m 187/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3707 - loss: 1.6919
[1m 215/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3701 - loss: 1.6937
[1m 243/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3703 - loss: 1.6934
[1m 269/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3710 - loss: 1.6921
[1m 296/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3716 - loss: 1.6912
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3719 - loss: 1.6908
[1m 348/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3722 - loss: 1.6901
[1m 377/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3725 - loss: 1.6897
[1m 405/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3729 - loss: 1.6891
[1m 433/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3733 - loss: 1.6885
[1m 459/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3735 - loss: 1.6882
[1m 485/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3737 - loss: 1.6879
[1m 513/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3739 - loss: 1.6876
[1m 541/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3741 - loss: 1.6872
[1m 567/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3744 - loss: 1.6869
[1m 596/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3747 - loss: 1.6865
[1m 622/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3750 - loss: 1.6860
[1m 645/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3752 - loss: 1.6857
[1m 670/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3754 - loss: 1.6853
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3757 - loss: 1.6849
[1m 722/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3760 - loss: 1.6844
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3762 - loss: 1.6838
[1m 776/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3764 - loss: 1.6834
[1m 803/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3766 - loss: 1.6829
[1m 829/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3768 - loss: 1.6824
[1m 858/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3770 - loss: 1.6819
[1m 883/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3772 - loss: 1.6814
[1m 911/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3773 - loss: 1.6809
[1m 937/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.6804
[1m 965/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3776 - loss: 1.6799
[1m 992/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.6794
[1m1019/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3779 - loss: 1.6789
[1m1045/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3780 - loss: 1.6784
[1m1073/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3782 - loss: 1.6780
[1m1098/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.6777
[1m1127/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3784 - loss: 1.6773
[1m1154/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.6770
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3786 - loss: 1.6768 - val_accuracy: 0.3730 - val_loss: 1.7652
Epoch 21/21

[1m   1/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7064
[1m  25/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3731 - loss: 1.6555  
[1m  51/1168[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3860 - loss: 1.6250
[1m  78/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3937 - loss: 1.6122
[1m 105/1168[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3979 - loss: 1.6112
[1m 132/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3978 - loss: 1.6135
[1m 158/1168[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6178
[1m 183/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3964 - loss: 1.6208
[1m 211/1168[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6220
[1m 238/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3961 - loss: 1.6223
[1m 266/1168[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6231
[1m 294/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3962 - loss: 1.6232
[1m 321/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6228
[1m 347/1168[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6225
[1m 374/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6225
[1m 402/1168[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6226
[1m 428/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6227
[1m 455/1168[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3971 - loss: 1.6228
[1m 483/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6233
[1m 512/1168[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3970 - loss: 1.6238
[1m 540/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6243
[1m 562/1168[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6246
[1m 587/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3969 - loss: 1.6249
[1m 612/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6252
[1m 640/1168[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6258
[1m 667/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3968 - loss: 1.6263
[1m 693/1168[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3967 - loss: 1.6267
[1m 723/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3966 - loss: 1.6273
[1m 749/1168[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3965 - loss: 1.6278
[1m 775/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3964 - loss: 1.6284
[1m 802/1168[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3963 - loss: 1.6289
[1m 827/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3962 - loss: 1.6295
[1m 854/1168[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3960 - loss: 1.6301
[1m 881/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3959 - loss: 1.6307
[1m 908/1168[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3958 - loss: 1.6311
[1m 936/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3957 - loss: 1.6316
[1m 964/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3956 - loss: 1.6319
[1m 991/1168[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3955 - loss: 1.6322
[1m1017/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3954 - loss: 1.6325
[1m1043/1168[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3953 - loss: 1.6328
[1m1072/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3952 - loss: 1.6330
[1m1100/1168[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6333
[1m1129/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6335
[1m1158/1168[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3951 - loss: 1.6337
[1m1168/1168[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3950 - loss: 1.6338 - val_accuracy: 0.3767 - val_loss: 1.8009

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 1s/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 2025-10-31 16:00:29.588229: I external/local_xla/xla/stream_executor/cuda/subprocess_compilation.cc:346] ptxas warning : Registers are spilled to local memory in function 'gemm_fusion_dot_196', 4 bytes spill stores, 4 bytes spill loads


[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step
Saved model to disk.
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:27[0m 1s/step
[1m 49/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m103/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 987us/step
[1m162/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 936us/step
[1m218/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 925us/step
[1m274/584[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 921us/step
[1m325/584[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 934us/step
[1m380/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 932us/step
[1m434/584[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 932us/step
[1m484/584[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 941us/step
[1m533/584[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 949us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 964us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 997us/step
[1m107/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 954us/step
[1m160/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 954us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 36.74 [%]
Global F1 score (validation) = 34.11 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.22493061 0.24587634 0.18726356 ... 0.00141683 0.13770619 0.01072906]
 [0.19828787 0.24133667 0.16182071 ... 0.00468843 0.11899249 0.00925177]
 [0.24667208 0.21915254 0.1776352  ... 0.00592875 0.17319429 0.02889341]
 ...
 [0.24709353 0.2371823  0.21054332 ... 0.00086964 0.15627469 0.01175518]
 [0.22748178 0.26465318 0.1931269  ... 0.00132777 0.12865524 0.00668619]
 [0.23223111 0.24640357 0.21189585 ... 0.00071306 0.1419776  0.00800325]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 46.53 [%]
Global accuracy score (test) = 33.76 [%]
Global F1 score (train) = 44.42 [%]
Global F1 score (test) = 31.77 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.22      0.36      0.27       184
 CAMINAR CON MÓVIL O LIBRO       0.20      0.36      0.26       184
       CAMINAR USUAL SPEED       0.10      0.01      0.02       184
            CAMINAR ZIGZAG       0.52      0.54      0.53       184
          DE PIE BARRIENDO       0.27      0.31      0.29       184
   DE PIE DOBLANDO TOALLAS       0.30      0.18      0.23       184
    DE PIE MOVIENDO LIBROS       0.32      0.48      0.38       184
          DE PIE USANDO PC       0.38      0.54      0.44       184
        FASE REPOSO CON K5       0.63      0.62      0.63       184
INCREMENTAL CICLOERGOMETRO       0.59      0.49      0.54       184
           SENTADO LEYENDO       0.30      0.26      0.28       184
         SENTADO USANDO PC       0.00      0.00      0.00       184
      SENTADO VIENDO LA TV       0.23      0.34      0.27       184
   SUBIR Y BAJAR ESCALERAS       0.36      0.08      0.13       184
                    TROTAR       0.47      0.50      0.49       161

                  accuracy                           0.34      2737
                 macro avg       0.33      0.34      0.32      2737
              weighted avg       0.32      0.34      0.32      2737


Accuracy capturado en la ejecución 29: 33.76 [%]
F1-score capturado en la ejecución 29: 31.77 [%]

=== EJECUCIÓN 30 ===

--- TRAIN (ejecución 30) ---

--- TEST (ejecución 30) ---
['CAMINAR CON LA COMPRA' 'CAMINAR CON MÓVIL O LIBRO' 'CAMINAR USUAL SPEED'
 'CAMINAR ZIGZAG' 'DE PIE BARRIENDO' 'DE PIE DOBLANDO TOALLAS'
 'DE PIE MOVIENDO LIBROS' 'DE PIE USANDO PC' 'FASE REPOSO CON K5'
 'INCREMENTAL CICLOERGOMETRO' 'SENTADO LEYENDO' 'SENTADO USANDO PC'
 'SENTADO VIENDO LA TV' 'SUBIR Y BAJAR ESCALERAS' 'TROTAR']
15
Mapeo de etiquetas: {'CAMINAR CON LA COMPRA': 0, 'CAMINAR CON MÓVIL O LIBRO': 1, 'CAMINAR USUAL SPEED': 2, 'CAMINAR ZIGZAG': 3, 'DE PIE BARRIENDO': 4, 'DE PIE DOBLANDO TOALLAS': 5, 'DE PIE MOVIENDO LIBROS': 6, 'DE PIE USANDO PC': 7, 'FASE REPOSO CON K5': 8, 'INCREMENTAL CICLOERGOMETRO': 9, 'SENTADO LEYENDO': 10, 'SENTADO USANDO PC': 11, 'SENTADO VIENDO LA TV': 12, 'SUBIR Y BAJAR ESCALERAS': 13, 'TROTAR': 14}
Loaded model from disk.
(2737, 6, 250)
(18676, 6, 250)

[1m  1/584[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12:30[0m 1s/step
[1m 50/584[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m102/584[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m159/584[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 958us/step
[1m206/584[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 985us/step
[1m260/584[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 978us/step
[1m310/584[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 986us/step
[1m362/584[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 983us/step
[1m407/584[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 999us/step
[1m458/584[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 998us/step
[1m510/584[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 994us/step
[1m561/584[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 994us/step
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step  
[1m584/584[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 3ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 12ms/step

[1m  1/169[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 52/169[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 991us/step
[1m104/169[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 989us/step
[1m155/169[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 989us/step
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step  
[1m169/169[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step
Global accuracy score (validation) = 37.67 [%]
Global F1 score (validation) = 34.56 [%]
[[ 2.]
 [ 2.]
 [ 2.]
 ...
 [13.]
 [13.]
 [13.]]
(2737, 1)
[[0.25309315 0.20453897 0.23138796 ... 0.00170675 0.19969255 0.03632053]
 [0.1783408  0.2341773  0.15462327 ... 0.00666613 0.10999301 0.00594329]
 [0.22906801 0.2461767  0.20197652 ... 0.00365637 0.1590335  0.00839583]
 ...
 [0.13057445 0.18179311 0.1141452  ... 0.00367939 0.08664382 0.00375889]
 [0.21795404 0.21487236 0.2009811  ... 0.00079428 0.1646898  0.00576715]
 [0.23918721 0.24897213 0.2080121  ... 0.00260414 0.15315603 0.00804104]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 45.8 [%]
Global accuracy score (test) = 33.39 [%]
Global F1 score (train) = 42.52 [%]
Global F1 score (test) = 32.09 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.16      0.26      0.20       184
 CAMINAR CON MÓVIL O LIBRO       0.22      0.40      0.28       184
       CAMINAR USUAL SPEED       0.09      0.02      0.03       184
            CAMINAR ZIGZAG       0.45      0.46      0.45       184
          DE PIE BARRIENDO       0.28      0.43      0.34       184
   DE PIE DOBLANDO TOALLAS       0.35      0.11      0.17       184
    DE PIE MOVIENDO LIBROS       0.33      0.50      0.40       184
          DE PIE USANDO PC       0.28      0.60      0.38       184
        FASE REPOSO CON K5       0.92      0.50      0.65       184
INCREMENTAL CICLOERGOMETRO       0.72      0.48      0.58       184
           SENTADO LEYENDO       0.24      0.18      0.21       184
         SENTADO USANDO PC       0.33      0.32      0.33       184
      SENTADO VIENDO LA TV       0.50      0.35      0.41       184
   SUBIR Y BAJAR ESCALERAS       0.15      0.01      0.02       184
                    TROTAR       0.35      0.39      0.37       161

                  accuracy                           0.33      2737
                 macro avg       0.36      0.33      0.32      2737
              weighted avg       0.36      0.33      0.32      2737


Accuracy capturado en la ejecución 30: 33.39 [%]
F1-score capturado en la ejecución 30: 32.09 [%]

=== RESUMEN FINAL ===
Accuracies: [33.14, 34.86, 34.45, 34.42, 33.07, 31.42, 32.23, 34.05, 31.64, 30.95, 33.36, 32.92, 33.76, 35.44, 33.98, 32.85, 33.72, 30.65, 33.14, 34.89, 33.76, 33.36, 35.18, 32.01, 34.02, 29.41, 32.96, 34.78, 33.76, 33.39]
F1-scores: [31.03, 33.28, 32.76, 34.36, 30.42, 28.49, 30.17, 32.98, 28.84, 29.03, 30.96, 30.01, 31.91, 33.8, 31.67, 31.12, 31.52, 28.2, 30.92, 30.48, 32.03, 30.93, 33.54, 29.89, 32.07, 26.67, 30.0, 31.98, 31.77, 32.09]
Accuracy mean: 33.2523 | std: 1.3843
F1 mean: 31.0973 | std: 1.7319

Resultados guardados en /mnt/nvme1n2/git/uniovi-simur-wearablepermed-data/output/Paper_results/cases_dataset_C/case_C_CAPTURE24_acc_gyr_17_classes/metrics_test.npz
